diff --git a/translations/hi/.co-op-translator.json b/translations/hi/.co-op-translator.json new file mode 100644 index 000000000..a4d0169ac --- /dev/null +++ b/translations/hi/.co-op-translator.json @@ -0,0 +1,596 @@ +{ + "1-Introduction/1-intro-to-ML/README.md": { + "original_hash": "69389392fa6346e0dfa30f664b7b6fec", + "translation_date": "2025-09-05T10:24:35+00:00", + "source_file": "1-Introduction/1-intro-to-ML/README.md", + "language_code": "hi" + }, + "1-Introduction/1-intro-to-ML/assignment.md": { + "original_hash": "4c4698044bb8af52cfb6388a4ee0e53b", + "translation_date": "2025-09-03T23:38:49+00:00", + "source_file": "1-Introduction/1-intro-to-ML/assignment.md", + "language_code": "hi" + }, + "1-Introduction/2-history-of-ML/README.md": { + "original_hash": "6a05fec147e734c3e6bfa54505648e2b", + "translation_date": "2025-09-05T10:25:07+00:00", + "source_file": "1-Introduction/2-history-of-ML/README.md", + "language_code": "hi" + }, + "1-Introduction/2-history-of-ML/assignment.md": { + "original_hash": "eb6e4d5afd1b21a57d2b9e6d0aac3969", + "translation_date": "2025-09-03T23:42:48+00:00", + "source_file": "1-Introduction/2-history-of-ML/assignment.md", + "language_code": "hi" + }, + "1-Introduction/3-fairness/README.md": { + "original_hash": "9a6b702d1437c0467e3c5c28d763dac2", + "translation_date": "2025-09-05T10:22:56+00:00", + "source_file": "1-Introduction/3-fairness/README.md", + "language_code": "hi" + }, + "1-Introduction/3-fairness/assignment.md": { + "original_hash": "dbda60e7b1fe5f18974e7858eff0004e", + "translation_date": "2025-09-03T23:31:36+00:00", + "source_file": "1-Introduction/3-fairness/assignment.md", + "language_code": "hi" + }, + "1-Introduction/4-techniques-of-ML/README.md": { + "original_hash": "9d91f3af3758fdd4569fb410575995ef", + "translation_date": "2025-09-05T10:23:54+00:00", + "source_file": "1-Introduction/4-techniques-of-ML/README.md", + "language_code": "hi" + }, + "1-Introduction/4-techniques-of-ML/assignment.md": { + "original_hash": "70d65aeddc06170bc1aed5b27805f930", + "translation_date": "2025-09-03T23:35:32+00:00", + "source_file": "1-Introduction/4-techniques-of-ML/assignment.md", + "language_code": "hi" + }, + "1-Introduction/README.md": { + "original_hash": "cf8ecc83f28e5b98051d2179eca08e08", + "translation_date": "2025-09-03T23:26:26+00:00", + "source_file": "1-Introduction/README.md", + "language_code": "hi" + }, + "2-Regression/1-Tools/README.md": { + "original_hash": "fa81d226c71d5af7a2cade31c1c92b88", + "translation_date": "2025-09-05T10:15:47+00:00", + "source_file": "2-Regression/1-Tools/README.md", + "language_code": "hi" + }, + "2-Regression/1-Tools/assignment.md": { + "original_hash": "74a5cf83e4ebc302afbcbc4f418afd0a", + "translation_date": "2025-09-03T22:36:37+00:00", + "source_file": "2-Regression/1-Tools/assignment.md", + "language_code": "hi" + }, + "2-Regression/1-Tools/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T22:36:57+00:00", + "source_file": "2-Regression/1-Tools/solution/Julia/README.md", + "language_code": "hi" + }, + "2-Regression/2-Data/README.md": { + "original_hash": "7c077988328ebfe33b24d07945f16eca", + "translation_date": "2025-09-05T10:16:34+00:00", + "source_file": "2-Regression/2-Data/README.md", + "language_code": "hi" + }, + "2-Regression/2-Data/assignment.md": { + "original_hash": "4485a1ed4dd1b5647365e3d87456515d", + "translation_date": "2025-09-03T22:40:40+00:00", + "source_file": "2-Regression/2-Data/assignment.md", + "language_code": "hi" + }, + "2-Regression/2-Data/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T22:41:00+00:00", + "source_file": "2-Regression/2-Data/solution/Julia/README.md", + "language_code": "hi" + }, + "2-Regression/3-Linear/README.md": { + "original_hash": "40e64f004f3cb50aa1d8661672d3cd92", + "translation_date": "2025-09-05T10:12:48+00:00", + "source_file": "2-Regression/3-Linear/README.md", + "language_code": "hi" + }, + "2-Regression/3-Linear/assignment.md": { + "original_hash": "cc471fa89c293bc735dd3a9a0fb79b1b", + "translation_date": "2025-09-03T22:22:25+00:00", + "source_file": "2-Regression/3-Linear/assignment.md", + "language_code": "hi" + }, + "2-Regression/3-Linear/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T22:22:46+00:00", + "source_file": "2-Regression/3-Linear/solution/Julia/README.md", + "language_code": "hi" + }, + "2-Regression/4-Logistic/README.md": { + "original_hash": "abf86d845c84330bce205a46b382ec88", + "translation_date": "2025-09-05T10:14:06+00:00", + "source_file": "2-Regression/4-Logistic/README.md", + "language_code": "hi" + }, + "2-Regression/4-Logistic/assignment.md": { + "original_hash": "8af40209a41494068c1f42b14c0b450d", + "translation_date": "2025-09-03T22:31:32+00:00", + "source_file": "2-Regression/4-Logistic/assignment.md", + "language_code": "hi" + }, + "2-Regression/4-Logistic/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T22:31:52+00:00", + "source_file": "2-Regression/4-Logistic/solution/Julia/README.md", + "language_code": "hi" + }, + "2-Regression/README.md": { + "original_hash": "508582278dbb8edd2a8a80ac96ef416c", + "translation_date": "2025-09-03T22:15:54+00:00", + "source_file": "2-Regression/README.md", + "language_code": "hi" + }, + "3-Web-App/1-Web-App/README.md": { + "original_hash": "e0b75f73e4a90d45181dc5581fe2ef5c", + "translation_date": "2025-09-05T10:25:48+00:00", + "source_file": "3-Web-App/1-Web-App/README.md", + "language_code": "hi" + }, + "3-Web-App/1-Web-App/assignment.md": { + "original_hash": "a8e8ae10be335cbc745b75ee552317ff", + "translation_date": "2025-09-03T23:47:33+00:00", + "source_file": "3-Web-App/1-Web-App/assignment.md", + "language_code": "hi" + }, + "3-Web-App/README.md": { + "original_hash": "9836ff53cfef716ddfd70e06c5f43436", + "translation_date": "2025-09-03T23:43:37+00:00", + "source_file": "3-Web-App/README.md", + "language_code": "hi" + }, + "4-Classification/1-Introduction/README.md": { + "original_hash": "aaf391d922bd6de5efba871d514c6d47", + "translation_date": "2025-09-05T10:28:19+00:00", + "source_file": "4-Classification/1-Introduction/README.md", + "language_code": "hi" + }, + "4-Classification/1-Introduction/assignment.md": { + "original_hash": "b2a01912beb24cfb0007f83594dba801", + "translation_date": "2025-09-04T00:04:23+00:00", + "source_file": "4-Classification/1-Introduction/assignment.md", + "language_code": "hi" + }, + "4-Classification/1-Introduction/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-04T00:04:45+00:00", + "source_file": "4-Classification/1-Introduction/solution/Julia/README.md", + "language_code": "hi" + }, + "4-Classification/2-Classifiers-1/README.md": { + "original_hash": "1a6e9e46b34a2e559fbbfc1f95397c7b", + "translation_date": "2025-09-05T10:26:26+00:00", + "source_file": "4-Classification/2-Classifiers-1/README.md", + "language_code": "hi" + }, + "4-Classification/2-Classifiers-1/assignment.md": { + "original_hash": "de6025f96841498b0577e9d1aee18d1f", + "translation_date": "2025-09-03T23:54:22+00:00", + "source_file": "4-Classification/2-Classifiers-1/assignment.md", + "language_code": "hi" + }, + "4-Classification/2-Classifiers-1/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T23:54:42+00:00", + "source_file": "4-Classification/2-Classifiers-1/solution/Julia/README.md", + "language_code": "hi" + }, + "4-Classification/3-Classifiers-2/README.md": { + "original_hash": "49047911108adc49d605cddfb455749c", + "translation_date": "2025-09-05T10:27:55+00:00", + "source_file": "4-Classification/3-Classifiers-2/README.md", + "language_code": "hi" + }, + "4-Classification/3-Classifiers-2/assignment.md": { + "original_hash": "58dfdaf79fb73f7d34b22bdbacf57329", + "translation_date": "2025-09-04T00:00:27+00:00", + "source_file": "4-Classification/3-Classifiers-2/assignment.md", + "language_code": "hi" + }, + "4-Classification/3-Classifiers-2/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-04T00:01:00+00:00", + "source_file": "4-Classification/3-Classifiers-2/solution/Julia/README.md", + "language_code": "hi" + }, + "4-Classification/4-Applied/README.md": { + "original_hash": "61bdec27ed2da8b098cd9065405d9bb0", + "translation_date": "2025-09-05T10:27:19+00:00", + "source_file": "4-Classification/4-Applied/README.md", + "language_code": "hi" + }, + "4-Classification/4-Applied/assignment.md": { + "original_hash": "799ed651e2af0a7cad17c6268db11578", + "translation_date": "2025-09-03T23:57:45+00:00", + "source_file": "4-Classification/4-Applied/assignment.md", + "language_code": "hi" + }, + "4-Classification/README.md": { + "original_hash": "74e809ffd1e613a1058bbc3e9600859e", + "translation_date": "2025-09-03T23:49:28+00:00", + "source_file": "4-Classification/README.md", + "language_code": "hi" + }, + "5-Clustering/1-Visualize/README.md": { + "original_hash": "730225ea274c9174fe688b21d421539d", + "translation_date": "2025-09-05T10:19:12+00:00", + "source_file": "5-Clustering/1-Visualize/README.md", + "language_code": "hi" + }, + "5-Clustering/1-Visualize/assignment.md": { + "original_hash": "589fa015a5e7d9e67bd629f7d47b53de", + "translation_date": "2025-09-03T23:09:32+00:00", + "source_file": "5-Clustering/1-Visualize/assignment.md", + "language_code": "hi" + }, + "5-Clustering/1-Visualize/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T23:09:55+00:00", + "source_file": "5-Clustering/1-Visualize/solution/Julia/README.md", + "language_code": "hi" + }, + "5-Clustering/2-K-Means/README.md": { + "original_hash": "7cdd17338d9bbd7e2171c2cd462eb081", + "translation_date": "2025-09-05T10:20:37+00:00", + "source_file": "5-Clustering/2-K-Means/README.md", + "language_code": "hi" + }, + "5-Clustering/2-K-Means/assignment.md": { + "original_hash": "b8e17eff34ad1680eba2a5d3cf9ffc41", + "translation_date": "2025-09-03T23:13:08+00:00", + "source_file": "5-Clustering/2-K-Means/assignment.md", + "language_code": "hi" + }, + "5-Clustering/2-K-Means/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T23:13:27+00:00", + "source_file": "5-Clustering/2-K-Means/solution/Julia/README.md", + "language_code": "hi" + }, + "5-Clustering/README.md": { + "original_hash": "b28a3a4911584062772c537b653ebbc7", + "translation_date": "2025-09-03T22:56:31+00:00", + "source_file": "5-Clustering/README.md", + "language_code": "hi" + }, + "6-NLP/1-Introduction-to-NLP/README.md": { + "original_hash": "1c2ec40cf55c98a028a359c27ef7e45a", + "translation_date": "2025-09-05T10:34:16+00:00", + "source_file": "6-NLP/1-Introduction-to-NLP/README.md", + "language_code": "hi" + }, + "6-NLP/1-Introduction-to-NLP/assignment.md": { + "original_hash": "1d7583e8046dacbb0c056d5ba0a71b16", + "translation_date": "2025-09-04T00:49:28+00:00", + "source_file": "6-NLP/1-Introduction-to-NLP/assignment.md", + "language_code": "hi" + }, + "6-NLP/2-Tasks/README.md": { + "original_hash": "5f3cb462e3122e1afe7ab0050ccf2bd3", + "translation_date": "2025-09-05T10:31:35+00:00", + "source_file": "6-NLP/2-Tasks/README.md", + "language_code": "hi" + }, + "6-NLP/2-Tasks/assignment.md": { + "original_hash": "2efc4c2aba5ed06c780c05539c492ae3", + "translation_date": "2025-09-04T00:37:37+00:00", + "source_file": "6-NLP/2-Tasks/assignment.md", + "language_code": "hi" + }, + "6-NLP/3-Translation-Sentiment/README.md": { + "original_hash": "be03c8182982b87ced155e4e9d1438e8", + "translation_date": "2025-09-05T10:34:53+00:00", + "source_file": "6-NLP/3-Translation-Sentiment/README.md", + "language_code": "hi" + }, + "6-NLP/3-Translation-Sentiment/assignment.md": { + "original_hash": "9d2a734deb904caff310d1a999c6bd7a", + "translation_date": "2025-09-04T00:54:15+00:00", + "source_file": "6-NLP/3-Translation-Sentiment/assignment.md", + "language_code": "hi" + }, + "6-NLP/3-Translation-Sentiment/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-04T00:54:55+00:00", + "source_file": "6-NLP/3-Translation-Sentiment/solution/Julia/README.md", + "language_code": "hi" + }, + "6-NLP/3-Translation-Sentiment/solution/R/README.md": { + "original_hash": "81db6ff2cf6e62fbe2340b094bb9509e", + "translation_date": "2025-09-04T00:54:37+00:00", + "source_file": "6-NLP/3-Translation-Sentiment/solution/R/README.md", + "language_code": "hi" + }, + "6-NLP/4-Hotel-Reviews-1/README.md": { + "original_hash": "8d32dadeda93c6fb5c43619854882ab1", + "translation_date": "2025-09-05T10:32:20+00:00", + "source_file": "6-NLP/4-Hotel-Reviews-1/README.md", + "language_code": "hi" + }, + "6-NLP/4-Hotel-Reviews-1/assignment.md": { + "original_hash": "bf39bceb833cd628f224941dca8041df", + "translation_date": "2025-09-04T00:44:42+00:00", + "source_file": "6-NLP/4-Hotel-Reviews-1/assignment.md", + "language_code": "hi" + }, + "6-NLP/4-Hotel-Reviews-1/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-04T00:45:21+00:00", + "source_file": "6-NLP/4-Hotel-Reviews-1/solution/Julia/README.md", + "language_code": "hi" + }, + "6-NLP/4-Hotel-Reviews-1/solution/R/README.md": { + "original_hash": "81db6ff2cf6e62fbe2340b094bb9509e", + "translation_date": "2025-09-04T00:45:03+00:00", + "source_file": "6-NLP/4-Hotel-Reviews-1/solution/R/README.md", + "language_code": "hi" + }, + "6-NLP/5-Hotel-Reviews-2/README.md": { + "original_hash": "2c742993fe95d5bcbb2846eda3d442a1", + "translation_date": "2025-09-05T10:35:41+00:00", + "source_file": "6-NLP/5-Hotel-Reviews-2/README.md", + "language_code": "hi" + }, + "6-NLP/5-Hotel-Reviews-2/assignment.md": { + "original_hash": "daf144daa552da6a7d442aff6f3e77d8", + "translation_date": "2025-09-04T01:00:05+00:00", + "source_file": "6-NLP/5-Hotel-Reviews-2/assignment.md", + "language_code": "hi" + }, + "6-NLP/5-Hotel-Reviews-2/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-04T01:00:45+00:00", + "source_file": "6-NLP/5-Hotel-Reviews-2/solution/Julia/README.md", + "language_code": "hi" + }, + "6-NLP/5-Hotel-Reviews-2/solution/R/README.md": { + "original_hash": "81db6ff2cf6e62fbe2340b094bb9509e", + "translation_date": "2025-09-04T01:00:27+00:00", + "source_file": "6-NLP/5-Hotel-Reviews-2/solution/R/README.md", + "language_code": "hi" + }, + "6-NLP/README.md": { + "original_hash": "1eb379dc2d0c9940b320732d16083778", + "translation_date": "2025-09-04T00:33:39+00:00", + "source_file": "6-NLP/README.md", + "language_code": "hi" + }, + "6-NLP/data/README.md": { + "original_hash": "ee0670655c89e4719319764afb113624", + "translation_date": "2025-09-04T00:45:43+00:00", + "source_file": "6-NLP/data/README.md", + "language_code": "hi" + }, + "7-TimeSeries/1-Introduction/README.md": { + "original_hash": "662b509c39eee205687726636d0a8455", + "translation_date": "2025-09-05T10:18:02+00:00", + "source_file": "7-TimeSeries/1-Introduction/README.md", + "language_code": "hi" + }, + "7-TimeSeries/1-Introduction/assignment.md": { + "original_hash": "d1781b0b92568ea1d119d0a198b576b4", + "translation_date": "2025-09-03T22:51:10+00:00", + "source_file": "7-TimeSeries/1-Introduction/assignment.md", + "language_code": "hi" + }, + "7-TimeSeries/1-Introduction/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T22:51:49+00:00", + "source_file": "7-TimeSeries/1-Introduction/solution/Julia/README.md", + "language_code": "hi" + }, + "7-TimeSeries/1-Introduction/solution/R/README.md": { + "original_hash": "81db6ff2cf6e62fbe2340b094bb9509e", + "translation_date": "2025-09-03T22:51:32+00:00", + "source_file": "7-TimeSeries/1-Introduction/solution/R/README.md", + "language_code": "hi" + }, + "7-TimeSeries/2-ARIMA/README.md": { + "original_hash": "917dbf890db71a322f306050cb284749", + "translation_date": "2025-09-05T10:17:13+00:00", + "source_file": "7-TimeSeries/2-ARIMA/README.md", + "language_code": "hi" + }, + "7-TimeSeries/2-ARIMA/assignment.md": { + "original_hash": "1c814013e10866dfd92cdb32caaae3ac", + "translation_date": "2025-09-03T22:46:41+00:00", + "source_file": "7-TimeSeries/2-ARIMA/assignment.md", + "language_code": "hi" + }, + "7-TimeSeries/2-ARIMA/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T22:47:20+00:00", + "source_file": "7-TimeSeries/2-ARIMA/solution/Julia/README.md", + "language_code": "hi" + }, + "7-TimeSeries/2-ARIMA/solution/R/README.md": { + "original_hash": "81db6ff2cf6e62fbe2340b094bb9509e", + "translation_date": "2025-09-03T22:47:02+00:00", + "source_file": "7-TimeSeries/2-ARIMA/solution/R/README.md", + "language_code": "hi" + }, + "7-TimeSeries/3-SVR/README.md": { + "original_hash": "482bccabe1df958496ea71a3667995cd", + "translation_date": "2025-09-05T10:18:39+00:00", + "source_file": "7-TimeSeries/3-SVR/README.md", + "language_code": "hi" + }, + "7-TimeSeries/3-SVR/assignment.md": { + "original_hash": "94aa2fc6154252ae30a3f3740299707a", + "translation_date": "2025-09-03T22:55:24+00:00", + "source_file": "7-TimeSeries/3-SVR/assignment.md", + "language_code": "hi" + }, + "7-TimeSeries/README.md": { + "original_hash": "61342603bad8acadbc6b2e4e3aab3f66", + "translation_date": "2025-09-03T22:41:46+00:00", + "source_file": "7-TimeSeries/README.md", + "language_code": "hi" + }, + "8-Reinforcement/1-QLearning/README.md": { + "original_hash": "911efd5e595089000cb3c16fce1beab8", + "translation_date": "2025-09-05T10:29:57+00:00", + "source_file": "8-Reinforcement/1-QLearning/README.md", + "language_code": "hi" + }, + "8-Reinforcement/1-QLearning/assignment.md": { + "original_hash": "68394b2102d3503882e5e914bd0ff5c1", + "translation_date": "2025-09-04T00:24:59+00:00", + "source_file": "8-Reinforcement/1-QLearning/assignment.md", + "language_code": "hi" + }, + "8-Reinforcement/1-QLearning/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-04T00:25:42+00:00", + "source_file": "8-Reinforcement/1-QLearning/solution/Julia/README.md", + "language_code": "hi" + }, + "8-Reinforcement/1-QLearning/solution/R/README.md": { + "original_hash": "81db6ff2cf6e62fbe2340b094bb9509e", + "translation_date": "2025-09-04T00:25:25+00:00", + "source_file": "8-Reinforcement/1-QLearning/solution/R/README.md", + "language_code": "hi" + }, + "8-Reinforcement/2-Gym/README.md": { + "original_hash": "107d5bb29da8a562e7ae72262d251a75", + "translation_date": "2025-09-05T10:30:41+00:00", + "source_file": "8-Reinforcement/2-Gym/README.md", + "language_code": "hi" + }, + "8-Reinforcement/2-Gym/assignment.md": { + "original_hash": "1f2b7441745eb52e25745423b247016b", + "translation_date": "2025-09-04T00:32:02+00:00", + "source_file": "8-Reinforcement/2-Gym/assignment.md", + "language_code": "hi" + }, + "8-Reinforcement/2-Gym/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-04T00:32:48+00:00", + "source_file": "8-Reinforcement/2-Gym/solution/Julia/README.md", + "language_code": "hi" + }, + "8-Reinforcement/2-Gym/solution/R/README.md": { + "original_hash": "81db6ff2cf6e62fbe2340b094bb9509e", + "translation_date": "2025-09-04T00:32:30+00:00", + "source_file": "8-Reinforcement/2-Gym/solution/R/README.md", + "language_code": "hi" + }, + "8-Reinforcement/README.md": { + "original_hash": "20ca019012b1725de956681d036d8b18", + "translation_date": "2025-09-04T00:14:45+00:00", + "source_file": "8-Reinforcement/README.md", + "language_code": "hi" + }, + "9-Real-World/1-Applications/README.md": { + "original_hash": "83320d6b6994909e35d830cebf214039", + "translation_date": "2025-09-05T10:21:12+00:00", + "source_file": "9-Real-World/1-Applications/README.md", + "language_code": "hi" + }, + "9-Real-World/1-Applications/assignment.md": { + "original_hash": "fdebfcd0a3f12c9e2b436ded1aa79885", + "translation_date": "2025-09-03T23:19:53+00:00", + "source_file": "9-Real-World/1-Applications/assignment.md", + "language_code": "hi" + }, + "9-Real-World/2-Debugging-ML-Models/README.md": { + "original_hash": "df2b538e8fbb3e91cf0419ae2f858675", + "translation_date": "2025-09-05T10:21:53+00:00", + "source_file": "9-Real-World/2-Debugging-ML-Models/README.md", + "language_code": "hi" + }, + "9-Real-World/2-Debugging-ML-Models/assignment.md": { + "original_hash": "91c6a180ef08e20cc15acfd2d6d6e164", + "translation_date": "2025-09-03T23:25:40+00:00", + "source_file": "9-Real-World/2-Debugging-ML-Models/assignment.md", + "language_code": "hi" + }, + "9-Real-World/README.md": { + "original_hash": "5e069a0ac02a9606a69946c2b3c574a9", + "translation_date": "2025-09-03T23:15:03+00:00", + "source_file": "9-Real-World/README.md", + "language_code": "hi" + }, + "AGENTS.md": { + "original_hash": "93fdaa0fd38836e50c4793e2f2f25e8b", + "translation_date": "2025-10-03T11:02:59+00:00", + "source_file": "AGENTS.md", + "language_code": "hi" + }, + "CODE_OF_CONDUCT.md": { + "original_hash": "c06b12caf3c901eb3156e3dd5b0aea56", + "translation_date": "2025-09-03T22:14:48+00:00", + "source_file": "CODE_OF_CONDUCT.md", + "language_code": "hi" + }, + "CONTRIBUTING.md": { + "original_hash": "977ec5266dfd78ad1ce2bd8d46fccbda", + "translation_date": "2025-09-03T22:12:09+00:00", + "source_file": "CONTRIBUTING.md", + "language_code": "hi" + }, + "README.md": { + "original_hash": "da2ceed62f16a0820259556e3a873c95", + "translation_date": "2026-01-29T18:06:16+00:00", + "source_file": "README.md", + "language_code": "hi" + }, + "SECURITY.md": { + "original_hash": "5e1b8da31aae9cca3d53ad243fa3365a", + "translation_date": "2025-09-03T22:13:17+00:00", + "source_file": "SECURITY.md", + "language_code": "hi" + }, + "SUPPORT.md": { + "original_hash": "09623d7343ff1c26ff4f198c1b2d3176", + "translation_date": "2025-10-03T11:49:20+00:00", + "source_file": "SUPPORT.md", + "language_code": "hi" + }, + "TROUBLESHOOTING.md": { + "original_hash": "134d8759f0e2ab886e9aa4f62362c201", + "translation_date": "2025-10-03T12:40:53+00:00", + "source_file": "TROUBLESHOOTING.md", + "language_code": "hi" + }, + "docs/_sidebar.md": { + "original_hash": "68dd06c685f6ce840e0acfa313352e7c", + "translation_date": "2025-09-03T23:14:17+00:00", + "source_file": "docs/_sidebar.md", + "language_code": "hi" + }, + "for-teachers.md": { + "original_hash": "b37de02054fa6c0438ede6fabe1fdfb8", + "translation_date": "2025-09-03T22:14:14+00:00", + "source_file": "for-teachers.md", + "language_code": "hi" + }, + "quiz-app/README.md": { + "original_hash": "6d130dffca5db70d7e615f926cb1ad4c", + "translation_date": "2025-09-03T23:48:35+00:00", + "source_file": "quiz-app/README.md", + "language_code": "hi" + }, + "sketchnotes/LICENSE.md": { + "original_hash": "fba3b94d88bfb9b81369b869a1e9a20f", + "translation_date": "2025-09-04T00:12:53+00:00", + "source_file": "sketchnotes/LICENSE.md", + "language_code": "hi" + }, + "sketchnotes/README.md": { + "original_hash": "a88d5918c1b9da69a40d917a0840c497", + "translation_date": "2025-09-04T00:05:13+00:00", + "source_file": "sketchnotes/README.md", + "language_code": "hi" + } +} \ No newline at end of file diff --git a/translations/hi/1-Introduction/1-intro-to-ML/README.md b/translations/hi/1-Introduction/1-intro-to-ML/README.md index fb5521fa1..30db4f3c9 100644 --- a/translations/hi/1-Introduction/1-intro-to-ML/README.md +++ b/translations/hi/1-Introduction/1-intro-to-ML/README.md @@ -1,12 +1,3 @@ - # मशीन लर्निंग का परिचय ## [प्री-लेक्चर क्विज़](https://ff-quizzes.netlify.app/en/ml/) diff --git a/translations/hi/1-Introduction/1-intro-to-ML/assignment.md b/translations/hi/1-Introduction/1-intro-to-ML/assignment.md index 734bc7d23..c19554542 100644 --- a/translations/hi/1-Introduction/1-intro-to-ML/assignment.md +++ b/translations/hi/1-Introduction/1-intro-to-ML/assignment.md @@ -1,12 +1,3 @@ - # शुरू करें और काम करने के लिए तैयार हो जाएं ## निर्देश diff --git a/translations/hi/1-Introduction/2-history-of-ML/README.md b/translations/hi/1-Introduction/2-history-of-ML/README.md index 61a8ac3c3..01ce7d35f 100644 --- a/translations/hi/1-Introduction/2-history-of-ML/README.md +++ b/translations/hi/1-Introduction/2-history-of-ML/README.md @@ -1,12 +1,3 @@ - # मशीन लर्निंग का इतिहास ![मशीन लर्निंग के इतिहास का सारांश एक स्केच नोट में](../../../../sketchnotes/ml-history.png) diff --git a/translations/hi/1-Introduction/2-history-of-ML/assignment.md b/translations/hi/1-Introduction/2-history-of-ML/assignment.md index f87a730f6..ecab4e20e 100644 --- a/translations/hi/1-Introduction/2-history-of-ML/assignment.md +++ b/translations/hi/1-Introduction/2-history-of-ML/assignment.md @@ -1,12 +1,3 @@ - # एक टाइमलाइन बनाएं ## निर्देश diff --git a/translations/hi/1-Introduction/3-fairness/README.md b/translations/hi/1-Introduction/3-fairness/README.md index 2a743b371..faed8ad46 100644 --- a/translations/hi/1-Introduction/3-fairness/README.md +++ b/translations/hi/1-Introduction/3-fairness/README.md @@ -1,12 +1,3 @@ - # जिम्मेदार AI के साथ मशीन लर्निंग समाधान बनाना ![मशीन लर्निंग में जिम्मेदार AI का सारांश एक स्केच नोट में](../../../../sketchnotes/ml-fairness.png) diff --git a/translations/hi/1-Introduction/3-fairness/assignment.md b/translations/hi/1-Introduction/3-fairness/assignment.md index 48e6b67cd..1f41c47af 100644 --- a/translations/hi/1-Introduction/3-fairness/assignment.md +++ b/translations/hi/1-Introduction/3-fairness/assignment.md @@ -1,12 +1,3 @@ - # जिम्मेदार AI टूलबॉक्स का अन्वेषण करें ## निर्देश diff --git a/translations/hi/1-Introduction/4-techniques-of-ML/README.md b/translations/hi/1-Introduction/4-techniques-of-ML/README.md index 3d2d4ebba..4f86f3784 100644 --- a/translations/hi/1-Introduction/4-techniques-of-ML/README.md +++ b/translations/hi/1-Introduction/4-techniques-of-ML/README.md @@ -1,12 +1,3 @@ - # मशीन लर्निंग की तकनीकें मशीन लर्निंग मॉडल और उनके उपयोग और रखरखाव की प्रक्रिया अन्य विकास वर्कफ़्लो से काफी अलग होती है। इस पाठ में, हम इस प्रक्रिया को सरल बनाएंगे और उन मुख्य तकनीकों को समझाएंगे जिन्हें आपको जानना चाहिए। आप: diff --git a/translations/hi/1-Introduction/4-techniques-of-ML/assignment.md b/translations/hi/1-Introduction/4-techniques-of-ML/assignment.md index 45f69415c..0c232540a 100644 --- a/translations/hi/1-Introduction/4-techniques-of-ML/assignment.md +++ b/translations/hi/1-Introduction/4-techniques-of-ML/assignment.md @@ -1,12 +1,3 @@ - # डेटा वैज्ञानिक का साक्षात्कार करें ## निर्देश diff --git a/translations/hi/1-Introduction/README.md b/translations/hi/1-Introduction/README.md index 576a32090..8aedae04c 100644 --- a/translations/hi/1-Introduction/README.md +++ b/translations/hi/1-Introduction/README.md @@ -1,12 +1,3 @@ - # मशीन लर्निंग का परिचय इस पाठ्यक्रम के इस भाग में, आपको मशीन लर्निंग के क्षेत्र के मूलभूत अवधारणाओं, यह क्या है, इसकी इतिहास और शोधकर्ता इसे कैसे उपयोग करते हैं, के बारे में परिचित कराया जाएगा। चलिए, इस नए ML की दुनिया को साथ में खोजते हैं! diff --git a/translations/hi/2-Regression/1-Tools/README.md b/translations/hi/2-Regression/1-Tools/README.md index a3b0fce6c..f4e043828 100644 --- a/translations/hi/2-Regression/1-Tools/README.md +++ b/translations/hi/2-Regression/1-Tools/README.md @@ -1,12 +1,3 @@ - # Python और Scikit-learn के साथ रिग्रेशन मॉडल्स शुरू करें ![रिग्रेशन का स्केच नोट में सारांश](../../../../sketchnotes/ml-regression.png) diff --git a/translations/hi/2-Regression/1-Tools/assignment.md b/translations/hi/2-Regression/1-Tools/assignment.md index 0212b3c2d..510a98331 100644 --- a/translations/hi/2-Regression/1-Tools/assignment.md +++ b/translations/hi/2-Regression/1-Tools/assignment.md @@ -1,12 +1,3 @@ - # स्किकिट-लर्न के साथ रिग्रेशन ## निर्देश diff --git a/translations/hi/2-Regression/1-Tools/solution/Julia/README.md b/translations/hi/2-Regression/1-Tools/solution/Julia/README.md index fad8d2113..6d7a7d13a 100644 --- a/translations/hi/2-Regression/1-Tools/solution/Julia/README.md +++ b/translations/hi/2-Regression/1-Tools/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/2-Regression/2-Data/README.md b/translations/hi/2-Regression/2-Data/README.md index b131a0038..5465bd77b 100644 --- a/translations/hi/2-Regression/2-Data/README.md +++ b/translations/hi/2-Regression/2-Data/README.md @@ -1,12 +1,3 @@ - # Scikit-learn का उपयोग करके एक रिग्रेशन मॉडल बनाएं: डेटा तैयार करें और विज़ुअलाइज़ करें ![डेटा विज़ुअलाइज़ेशन इन्फोग्राफिक](../../../../2-Regression/2-Data/images/data-visualization.png) diff --git a/translations/hi/2-Regression/2-Data/assignment.md b/translations/hi/2-Regression/2-Data/assignment.md index 2fabea620..3d34c7c84 100644 --- a/translations/hi/2-Regression/2-Data/assignment.md +++ b/translations/hi/2-Regression/2-Data/assignment.md @@ -1,12 +1,3 @@ - # विज़ुअलाइज़ेशन का अन्वेषण डेटा विज़ुअलाइज़ेशन के लिए कई अलग-अलग लाइब्रेरी उपलब्ध हैं। इस पाठ में कद्दू डेटा का उपयोग करके matplotlib और seaborn के साथ एक नमूना नोटबुक में कुछ विज़ुअलाइज़ेशन बनाएं। कौन सी लाइब्रेरी का उपयोग करना आसान है? diff --git a/translations/hi/2-Regression/2-Data/solution/Julia/README.md b/translations/hi/2-Regression/2-Data/solution/Julia/README.md index 21964cc88..6d7a7d13a 100644 --- a/translations/hi/2-Regression/2-Data/solution/Julia/README.md +++ b/translations/hi/2-Regression/2-Data/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/2-Regression/3-Linear/README.md b/translations/hi/2-Regression/3-Linear/README.md index 7cd96fb28..47bd44061 100644 --- a/translations/hi/2-Regression/3-Linear/README.md +++ b/translations/hi/2-Regression/3-Linear/README.md @@ -1,12 +1,3 @@ - # Scikit-learn का उपयोग करके एक रिग्रेशन मॉडल बनाएं: चार तरीकों से रिग्रेशन ![लिनियर बनाम पॉलिनोमियल रिग्रेशन इन्फोग्राफिक](../../../../2-Regression/3-Linear/images/linear-polynomial.png) @@ -114,11 +105,11 @@ day_of_year = pd.to_datetime(pumpkins['Date']).apply(lambda dt: (dt-datetime(dt. पिछले पाठ से आपने शायद देखा होगा कि विभिन्न महीनों के लिए औसत कीमत इस प्रकार दिखती है: -महीने के अनुसार औसत कीमत +महीने के अनुसार औसत कीमत यह सुझाव देता है कि कुछ सहसंबंध हो सकता है, और हम `Month` और `Price` के बीच, या `DayOfYear` और `Price` के बीच संबंध की भविष्यवाणी करने के लिए एक लिनियर रिग्रेशन मॉडल को प्रशिक्षित करने का प्रयास कर सकते हैं। यहाँ एक स्कैटरप्लॉट है जो बाद के संबंध को दिखाता है: -साल के दिन बनाम कीमत का स्कैटरप्लॉट +साल के दिन बनाम कीमत का स्कैटरप्लॉट आइए `corr` फ़ंक्शन का उपयोग करके देखें कि क्या कोई सहसंबंध है: @@ -137,7 +128,7 @@ for i,var in enumerate(new_pumpkins['Variety'].unique()): ax = df.plot.scatter('DayOfYear','Price',ax=ax,c=colors[i],label=var) ``` -साल के दिन बनाम कीमत का स्कैटरप्लॉट +साल के दिन बनाम कीमत का स्कैटरप्लॉट हमारी जांच से पता चलता है कि किस्म का समग्र कीमत पर तारीख की तुलना में अधिक प्रभाव है। हम इसे बार ग्राफ़ के साथ देख सकते हैं: @@ -145,7 +136,7 @@ for i,var in enumerate(new_pumpkins['Variety'].unique()): new_pumpkins.groupby('Variety')['Price'].mean().plot(kind='bar') ``` -किस्म बनाम कीमत का बार ग्राफ़ +किस्म बनाम कीमत का बार ग्राफ़ आइए फिलहाल केवल एक कद्दू की किस्म, 'पाई टाइप', पर ध्यान केंद्रित करें और देखें कि तारीख का कीमत पर क्या प्रभाव पड़ता है: @@ -153,7 +144,7 @@ new_pumpkins.groupby('Variety')['Price'].mean().plot(kind='bar') pie_pumpkins = new_pumpkins[new_pumpkins['Variety']=='PIE TYPE'] pie_pumpkins.plot.scatter('DayOfYear','Price') ``` -साल के दिन बनाम कीमत का स्कैटरप्लॉट +साल के दिन बनाम कीमत का स्कैटरप्लॉट यदि हम अब `corr` फ़ंक्शन का उपयोग करके `Price` और `DayOfYear` के बीच सहसंबंध की गणना करते हैं, तो हमें कुछ `-0.27` जैसा मिलेगा - जिसका अर्थ है कि एक भविष्यवाणी मॉडल को प्रशिक्षित करना समझ में आता है। @@ -227,7 +218,7 @@ plt.scatter(X_test,y_test) plt.plot(X_test,pred) ``` -Linear regression +Linear regression ## बहुपद रिग्रेशन @@ -256,7 +247,7 @@ pipeline.fit(X_train,y_train) पाइपलाइन का उपयोग उसी तरह किया जा सकता है जैसे मूल `LinearRegression` ऑब्जेक्ट का उपयोग किया जाता है, यानी हम पाइपलाइन को `fit` कर सकते हैं और फिर `predict` का उपयोग करके भविष्यवाणी परिणाम प्राप्त कर सकते हैं। यहां परीक्षण डेटा और अनुमानित वक्र दिखाने वाला ग्राफ है: -Polynomial regression +Polynomial regression बहुपद रिग्रेशन का उपयोग करके, हम थोड़ा कम MSE और थोड़ा अधिक निर्धारण प्राप्त कर सकते हैं, लेकिन यह बहुत महत्वपूर्ण नहीं है। हमें अन्य विशेषताओं को ध्यान में रखना होगा! @@ -274,7 +265,7 @@ pipeline.fit(X_train,y_train) यहां आप देख सकते हैं कि किस्म के आधार पर औसत कीमत कैसे बदलती है: -Average price by variety +Average price by variety किस्म को ध्यान में रखने के लिए, हमें पहले इसे संख्यात्मक रूप में बदलना होगा, या **एन्कोड** करना होगा। इसे करने के कई तरीके हैं: diff --git a/translations/hi/2-Regression/3-Linear/assignment.md b/translations/hi/2-Regression/3-Linear/assignment.md index 73eb303ee..7781debf9 100644 --- a/translations/hi/2-Regression/3-Linear/assignment.md +++ b/translations/hi/2-Regression/3-Linear/assignment.md @@ -1,12 +1,3 @@ - # एक रिग्रेशन मॉडल बनाएं ## निर्देश diff --git a/translations/hi/2-Regression/3-Linear/solution/Julia/README.md b/translations/hi/2-Regression/3-Linear/solution/Julia/README.md index 3ea16e7ef..6d7a7d13a 100644 --- a/translations/hi/2-Regression/3-Linear/solution/Julia/README.md +++ b/translations/hi/2-Regression/3-Linear/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/2-Regression/4-Logistic/README.md b/translations/hi/2-Regression/4-Logistic/README.md index 1d52535c0..5f1eb81e0 100644 --- a/translations/hi/2-Regression/4-Logistic/README.md +++ b/translations/hi/2-Regression/4-Logistic/README.md @@ -1,12 +1,3 @@ - # श्रेणियों की भविष्यवाणी के लिए लॉजिस्टिक रिग्रेशन ![लॉजिस्टिक बनाम लीनियर रिग्रेशन इन्फोग्राफिक](../../../../2-Regression/4-Logistic/images/linear-vs-logistic.png) diff --git a/translations/hi/2-Regression/4-Logistic/assignment.md b/translations/hi/2-Regression/4-Logistic/assignment.md index d4f4f4ea7..e7da7ce28 100644 --- a/translations/hi/2-Regression/4-Logistic/assignment.md +++ b/translations/hi/2-Regression/4-Logistic/assignment.md @@ -1,12 +1,3 @@ - # पुनः प्रयास करना कुछ प्रतिगमन ## निर्देश diff --git a/translations/hi/2-Regression/4-Logistic/solution/Julia/README.md b/translations/hi/2-Regression/4-Logistic/solution/Julia/README.md index 9a3d607e8..6d7a7d13a 100644 --- a/translations/hi/2-Regression/4-Logistic/solution/Julia/README.md +++ b/translations/hi/2-Regression/4-Logistic/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/2-Regression/README.md b/translations/hi/2-Regression/README.md index cb6ba3948..5d497d260 100644 --- a/translations/hi/2-Regression/README.md +++ b/translations/hi/2-Regression/README.md @@ -1,12 +1,3 @@ - # मशीन लर्निंग के लिए रिग्रेशन मॉडल ## क्षेत्रीय विषय: उत्तरी अमेरिका में कद्दू की कीमतों के लिए रिग्रेशन मॉडल 🎃 diff --git a/translations/hi/3-Web-App/1-Web-App/README.md b/translations/hi/3-Web-App/1-Web-App/README.md index b8d95a432..c96b51c77 100644 --- a/translations/hi/3-Web-App/1-Web-App/README.md +++ b/translations/hi/3-Web-App/1-Web-App/README.md @@ -1,12 +1,3 @@ - # वेब ऐप बनाएं जो ML मॉडल का उपयोग करे इस पाठ में, आप एक डेटा सेट पर ML मॉडल को प्रशिक्षित करेंगे जो अद्भुत है: _पिछली सदी में UFO देखे जाने की घटनाएं_, जो NUFORC के डेटाबेस से ली गई हैं। diff --git a/translations/hi/3-Web-App/1-Web-App/assignment.md b/translations/hi/3-Web-App/1-Web-App/assignment.md index 8e4e04598..7c042d734 100644 --- a/translations/hi/3-Web-App/1-Web-App/assignment.md +++ b/translations/hi/3-Web-App/1-Web-App/assignment.md @@ -1,12 +1,3 @@ - # एक अलग मॉडल आज़माएं ## निर्देश diff --git a/translations/hi/3-Web-App/README.md b/translations/hi/3-Web-App/README.md index d6cf9ddf1..8b03be0ab 100644 --- a/translations/hi/3-Web-App/README.md +++ b/translations/hi/3-Web-App/README.md @@ -1,12 +1,3 @@ - # अपने ML मॉडल का उपयोग करने के लिए एक वेब ऐप बनाएं इस पाठ्यक्रम के इस भाग में, आपको एक व्यावहारिक ML विषय से परिचित कराया जाएगा: कैसे अपने Scikit-learn मॉडल को एक फाइल के रूप में सेव करें जिसे वेब एप्लिकेशन के भीतर भविष्यवाणी करने के लिए उपयोग किया जा सके। एक बार मॉडल सेव हो जाने के बाद, आप सीखेंगे कि इसे Flask में बनाए गए वेब ऐप में कैसे उपयोग करें। सबसे पहले, आप कुछ डेटा का उपयोग करके एक मॉडल बनाएंगे जो UFO देखे जाने के बारे में है! फिर, आप एक वेब ऐप बनाएंगे जो आपको सेकंड की संख्या, अक्षांश और देशांतर मान दर्ज करने की अनुमति देगा ताकि यह भविष्यवाणी की जा सके कि किस देश ने UFO देखने की रिपोर्ट की है। diff --git a/translations/hi/4-Classification/1-Introduction/README.md b/translations/hi/4-Classification/1-Introduction/README.md index 2b8933210..92b0ab52c 100644 --- a/translations/hi/4-Classification/1-Introduction/README.md +++ b/translations/hi/4-Classification/1-Introduction/README.md @@ -1,12 +1,3 @@ - # वर्गीकरण का परिचय इन चार पाठों में, आप क्लासिक मशीन लर्निंग के एक महत्वपूर्ण पहलू - _वर्गीकरण_ - का अन्वेषण करेंगे। हम एशिया और भारत के सभी अद्भुत व्यंजनों के बारे में एक डेटासेट का उपयोग करके विभिन्न वर्गीकरण एल्गोरिदम का उपयोग करना सीखेंगे। उम्मीद है कि आप भूखे हैं! diff --git a/translations/hi/4-Classification/1-Introduction/assignment.md b/translations/hi/4-Classification/1-Introduction/assignment.md index 740540429..aca5ad6ea 100644 --- a/translations/hi/4-Classification/1-Introduction/assignment.md +++ b/translations/hi/4-Classification/1-Introduction/assignment.md @@ -1,12 +1,3 @@ - # वर्गीकरण विधियों का अन्वेषण करें ## निर्देश diff --git a/translations/hi/4-Classification/1-Introduction/solution/Julia/README.md b/translations/hi/4-Classification/1-Introduction/solution/Julia/README.md index d452132f4..e29156702 100644 --- a/translations/hi/4-Classification/1-Introduction/solution/Julia/README.md +++ b/translations/hi/4-Classification/1-Introduction/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/4-Classification/2-Classifiers-1/README.md b/translations/hi/4-Classification/2-Classifiers-1/README.md index 27d06cffe..fc042ebc2 100644 --- a/translations/hi/4-Classification/2-Classifiers-1/README.md +++ b/translations/hi/4-Classification/2-Classifiers-1/README.md @@ -1,12 +1,3 @@ - # व्यंजन वर्गीकरणकर्ता 1 इस पाठ में, आप पिछले पाठ से सहेजे गए डेटा सेट का उपयोग करेंगे, जिसमें संतुलित और साफ डेटा है, जो विभिन्न व्यंजनों के बारे में है। diff --git a/translations/hi/4-Classification/2-Classifiers-1/assignment.md b/translations/hi/4-Classification/2-Classifiers-1/assignment.md index 80bc97301..01944c9ef 100644 --- a/translations/hi/4-Classification/2-Classifiers-1/assignment.md +++ b/translations/hi/4-Classification/2-Classifiers-1/assignment.md @@ -1,12 +1,3 @@ - # सॉल्वर का अध्ययन करें ## निर्देश diff --git a/translations/hi/4-Classification/2-Classifiers-1/solution/Julia/README.md b/translations/hi/4-Classification/2-Classifiers-1/solution/Julia/README.md index 644431c77..6acad2ade 100644 --- a/translations/hi/4-Classification/2-Classifiers-1/solution/Julia/README.md +++ b/translations/hi/4-Classification/2-Classifiers-1/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/4-Classification/3-Classifiers-2/README.md b/translations/hi/4-Classification/3-Classifiers-2/README.md index 3fb6a8fd3..50a367b70 100644 --- a/translations/hi/4-Classification/3-Classifiers-2/README.md +++ b/translations/hi/4-Classification/3-Classifiers-2/README.md @@ -1,12 +1,3 @@ - # व्यंजन वर्गीकरणकर्ता 2 इस दूसरे वर्गीकरण पाठ में, आप संख्यात्मक डेटा को वर्गीकृत करने के और तरीके जानेंगे। आप यह भी समझेंगे कि एक वर्गीकरणकर्ता को दूसरे पर चुनने के क्या परिणाम हो सकते हैं। diff --git a/translations/hi/4-Classification/3-Classifiers-2/assignment.md b/translations/hi/4-Classification/3-Classifiers-2/assignment.md index 741a27a81..c502fca61 100644 --- a/translations/hi/4-Classification/3-Classifiers-2/assignment.md +++ b/translations/hi/4-Classification/3-Classifiers-2/assignment.md @@ -1,12 +1,3 @@ - # पैरामीटर प्ले ## निर्देश diff --git a/translations/hi/4-Classification/3-Classifiers-2/solution/Julia/README.md b/translations/hi/4-Classification/3-Classifiers-2/solution/Julia/README.md index b7f690ee7..06bdc5c40 100644 --- a/translations/hi/4-Classification/3-Classifiers-2/solution/Julia/README.md +++ b/translations/hi/4-Classification/3-Classifiers-2/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/4-Classification/4-Applied/README.md b/translations/hi/4-Classification/4-Applied/README.md index 25563e1c4..3e2f2b9b1 100644 --- a/translations/hi/4-Classification/4-Applied/README.md +++ b/translations/hi/4-Classification/4-Applied/README.md @@ -1,12 +1,3 @@ - # क्यूज़ीन रिकमेंडर वेब ऐप बनाएं इस पाठ में, आप पिछले पाठों में सीखी गई तकनीकों का उपयोग करके एक वर्गीकरण मॉडल बनाएंगे और इस श्रृंखला में उपयोग किए गए स्वादिष्ट क्यूज़ीन डेटासेट के साथ काम करेंगे। इसके अलावा, आप एक छोटा वेब ऐप बनाएंगे जो सेव किए गए मॉडल का उपयोग करेगा, और Onnx के वेब रनटाइम का लाभ उठाएगा। diff --git a/translations/hi/4-Classification/4-Applied/assignment.md b/translations/hi/4-Classification/4-Applied/assignment.md index b578424a8..4cd730ba3 100644 --- a/translations/hi/4-Classification/4-Applied/assignment.md +++ b/translations/hi/4-Classification/4-Applied/assignment.md @@ -1,12 +1,3 @@ - # एक अनुशंसा प्रणाली बनाएं ## निर्देश diff --git a/translations/hi/4-Classification/README.md b/translations/hi/4-Classification/README.md index ed15f2425..ae133dc2f 100644 --- a/translations/hi/4-Classification/README.md +++ b/translations/hi/4-Classification/README.md @@ -1,12 +1,3 @@ - # वर्गीकरण के साथ शुरुआत करें ## क्षेत्रीय विषय: स्वादिष्ट एशियाई और भारतीय व्यंजन 🍜 diff --git a/translations/hi/5-Clustering/1-Visualize/README.md b/translations/hi/5-Clustering/1-Visualize/README.md index 51948ff6b..8d2f5e1c5 100644 --- a/translations/hi/5-Clustering/1-Visualize/README.md +++ b/translations/hi/5-Clustering/1-Visualize/README.md @@ -1,12 +1,3 @@ - # क्लस्टरिंग का परिचय क्लस्टरिंग [अनुपरिक्षित शिक्षण](https://wikipedia.org/wiki/Unsupervised_learning) का एक प्रकार है, जिसमें यह माना जाता है कि डेटा सेट लेबल रहित है या इसके इनपुट्स को पहले से परिभाषित आउटपुट्स के साथ नहीं जोड़ा गया है। यह विभिन्न एल्गोरिदम का उपयोग करके लेबल रहित डेटा को छांटता है और डेटा में पहचाने गए पैटर्न के अनुसार समूह प्रदान करता है। diff --git a/translations/hi/5-Clustering/1-Visualize/assignment.md b/translations/hi/5-Clustering/1-Visualize/assignment.md index 3e5cd437b..80fcabd8a 100644 --- a/translations/hi/5-Clustering/1-Visualize/assignment.md +++ b/translations/hi/5-Clustering/1-Visualize/assignment.md @@ -1,12 +1,3 @@ - # क्लस्टरिंग के लिए अन्य विज़ुअलाइज़ेशन पर शोध करें ## निर्देश diff --git a/translations/hi/5-Clustering/1-Visualize/solution/Julia/README.md b/translations/hi/5-Clustering/1-Visualize/solution/Julia/README.md index b639796c5..6acad2ade 100644 --- a/translations/hi/5-Clustering/1-Visualize/solution/Julia/README.md +++ b/translations/hi/5-Clustering/1-Visualize/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/5-Clustering/2-K-Means/README.md b/translations/hi/5-Clustering/2-K-Means/README.md index 7a475ba4a..41e1a36ee 100644 --- a/translations/hi/5-Clustering/2-K-Means/README.md +++ b/translations/hi/5-Clustering/2-K-Means/README.md @@ -1,12 +1,3 @@ - # K-Means क्लस्टरिंग ## [Pre-lecture quiz](https://ff-quizzes.netlify.app/en/ml/) diff --git a/translations/hi/5-Clustering/2-K-Means/assignment.md b/translations/hi/5-Clustering/2-K-Means/assignment.md index 311130003..42628607e 100644 --- a/translations/hi/5-Clustering/2-K-Means/assignment.md +++ b/translations/hi/5-Clustering/2-K-Means/assignment.md @@ -1,12 +1,3 @@ - # विभिन्न क्लस्टरिंग विधियों को आज़माएं ## निर्देश diff --git a/translations/hi/5-Clustering/2-K-Means/solution/Julia/README.md b/translations/hi/5-Clustering/2-K-Means/solution/Julia/README.md index 98b867231..06bdc5c40 100644 --- a/translations/hi/5-Clustering/2-K-Means/solution/Julia/README.md +++ b/translations/hi/5-Clustering/2-K-Means/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/5-Clustering/README.md b/translations/hi/5-Clustering/README.md index 035cac68a..a68373efb 100644 --- a/translations/hi/5-Clustering/README.md +++ b/translations/hi/5-Clustering/README.md @@ -1,12 +1,3 @@ - # मशीन लर्निंग के लिए क्लस्टरिंग मॉडल क्लस्टरिंग एक मशीन लर्निंग कार्य है जिसमें समान वस्तुओं को खोजा जाता है और उन्हें समूहों में बांटा जाता है जिन्हें क्लस्टर्स कहा जाता है। अन्य मशीन लर्निंग दृष्टिकोणों से क्लस्टरिंग को अलग बनाता है कि यह प्रक्रिया स्वचालित रूप से होती है। वास्तव में, इसे सुपरवाइज्ड लर्निंग का उल्टा कहना उचित होगा। diff --git a/translations/hi/6-NLP/1-Introduction-to-NLP/README.md b/translations/hi/6-NLP/1-Introduction-to-NLP/README.md index 6ce91e9a0..715ceb9ba 100644 --- a/translations/hi/6-NLP/1-Introduction-to-NLP/README.md +++ b/translations/hi/6-NLP/1-Introduction-to-NLP/README.md @@ -1,12 +1,3 @@ - # प्राकृतिक भाषा प्रसंस्करण का परिचय यह पाठ *प्राकृतिक भाषा प्रसंस्करण*, जो *कंप्यूटेशनल भाषाविज्ञान* का एक उपक्षेत्र है, के संक्षिप्त इतिहास और महत्वपूर्ण अवधारणाओं को कवर करता है। diff --git a/translations/hi/6-NLP/1-Introduction-to-NLP/assignment.md b/translations/hi/6-NLP/1-Introduction-to-NLP/assignment.md index 5150e87da..390b5a0b6 100644 --- a/translations/hi/6-NLP/1-Introduction-to-NLP/assignment.md +++ b/translations/hi/6-NLP/1-Introduction-to-NLP/assignment.md @@ -1,12 +1,3 @@ - # एक बॉट की खोज करें ## निर्देश diff --git a/translations/hi/6-NLP/2-Tasks/README.md b/translations/hi/6-NLP/2-Tasks/README.md index f04ec402e..08e0105d0 100644 --- a/translations/hi/6-NLP/2-Tasks/README.md +++ b/translations/hi/6-NLP/2-Tasks/README.md @@ -1,12 +1,3 @@ - # सामान्य प्राकृतिक भाषा प्रसंस्करण कार्य और तकनीकें अधिकांश *प्राकृतिक भाषा प्रसंस्करण* कार्यों के लिए, जिस पाठ को संसाधित करना है, उसे तोड़ना, जांचना और परिणामों को नियमों और डेटा सेट्स के साथ संग्रहीत या क्रॉस-रेफरेंस करना आवश्यक होता है। ये कार्य प्रोग्रामर को पाठ में शब्दों और शब्दावली की _अर्थ_ या _इरादा_ या केवल _आवृत्ति_ को समझने में मदद करते हैं। diff --git a/translations/hi/6-NLP/2-Tasks/assignment.md b/translations/hi/6-NLP/2-Tasks/assignment.md index 8d4b3d445..db18f854f 100644 --- a/translations/hi/6-NLP/2-Tasks/assignment.md +++ b/translations/hi/6-NLP/2-Tasks/assignment.md @@ -1,12 +1,3 @@ - # एक बॉट को जवाब देने वाला बनाएं ## निर्देश diff --git a/translations/hi/6-NLP/3-Translation-Sentiment/README.md b/translations/hi/6-NLP/3-Translation-Sentiment/README.md index 9a0d31271..4e17b90ca 100644 --- a/translations/hi/6-NLP/3-Translation-Sentiment/README.md +++ b/translations/hi/6-NLP/3-Translation-Sentiment/README.md @@ -1,12 +1,3 @@ - # मशीन लर्निंग के साथ अनुवाद और भावना विश्लेषण पिछले पाठों में आपने `TextBlob` का उपयोग करके एक बुनियादी बॉट बनाना सीखा, जो एक लाइब्रेरी है जो पीछे से मशीन लर्निंग का उपयोग करके संज्ञा वाक्यांश निकालने जैसे बुनियादी प्राकृतिक भाषा प्रसंस्करण (NLP) कार्य करती है। कंप्यूटेशनल भाषाविज्ञान में एक और महत्वपूर्ण चुनौती है एक भाषा से दूसरी भाषा में वाक्य का सटीक _अनुवाद_। diff --git a/translations/hi/6-NLP/3-Translation-Sentiment/assignment.md b/translations/hi/6-NLP/3-Translation-Sentiment/assignment.md index 1eb6a89eb..866ed2774 100644 --- a/translations/hi/6-NLP/3-Translation-Sentiment/assignment.md +++ b/translations/hi/6-NLP/3-Translation-Sentiment/assignment.md @@ -1,12 +1,3 @@ - # काव्यात्मक स्वतंत्रता ## निर्देश diff --git a/translations/hi/6-NLP/3-Translation-Sentiment/solution/Julia/README.md b/translations/hi/6-NLP/3-Translation-Sentiment/solution/Julia/README.md index 79c96b647..06bdc5c40 100644 --- a/translations/hi/6-NLP/3-Translation-Sentiment/solution/Julia/README.md +++ b/translations/hi/6-NLP/3-Translation-Sentiment/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/6-NLP/3-Translation-Sentiment/solution/R/README.md b/translations/hi/6-NLP/3-Translation-Sentiment/solution/R/README.md index f72d72153..e9e9c119f 100644 --- a/translations/hi/6-NLP/3-Translation-Sentiment/solution/R/README.md +++ b/translations/hi/6-NLP/3-Translation-Sentiment/solution/R/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/6-NLP/4-Hotel-Reviews-1/README.md b/translations/hi/6-NLP/4-Hotel-Reviews-1/README.md index de37b1230..597ecdf14 100644 --- a/translations/hi/6-NLP/4-Hotel-Reviews-1/README.md +++ b/translations/hi/6-NLP/4-Hotel-Reviews-1/README.md @@ -1,12 +1,3 @@ - # होटल समीक्षाओं के साथ भावना विश्लेषण - डेटा को संसाधित करना इस खंड में, आप पिछले पाठों में सीखी गई तकनीकों का उपयोग करके एक बड़े डेटा सेट का अन्वेषणात्मक डेटा विश्लेषण करेंगे। जब आपको विभिन्न कॉलमों की उपयोगिता का अच्छा समझ आ जाएगा, तो आप सीखेंगे: diff --git a/translations/hi/6-NLP/4-Hotel-Reviews-1/assignment.md b/translations/hi/6-NLP/4-Hotel-Reviews-1/assignment.md index 87f7849cd..7e84d9630 100644 --- a/translations/hi/6-NLP/4-Hotel-Reviews-1/assignment.md +++ b/translations/hi/6-NLP/4-Hotel-Reviews-1/assignment.md @@ -1,12 +1,3 @@ - # NLTK ## निर्देश diff --git a/translations/hi/6-NLP/4-Hotel-Reviews-1/solution/Julia/README.md b/translations/hi/6-NLP/4-Hotel-Reviews-1/solution/Julia/README.md index 342ae0b99..06bdc5c40 100644 --- a/translations/hi/6-NLP/4-Hotel-Reviews-1/solution/Julia/README.md +++ b/translations/hi/6-NLP/4-Hotel-Reviews-1/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/6-NLP/4-Hotel-Reviews-1/solution/R/README.md b/translations/hi/6-NLP/4-Hotel-Reviews-1/solution/R/README.md index b895f567c..f5b86aaa6 100644 --- a/translations/hi/6-NLP/4-Hotel-Reviews-1/solution/R/README.md +++ b/translations/hi/6-NLP/4-Hotel-Reviews-1/solution/R/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/6-NLP/5-Hotel-Reviews-2/README.md b/translations/hi/6-NLP/5-Hotel-Reviews-2/README.md index e521b755f..bf15594e5 100644 --- a/translations/hi/6-NLP/5-Hotel-Reviews-2/README.md +++ b/translations/hi/6-NLP/5-Hotel-Reviews-2/README.md @@ -1,12 +1,3 @@ - # होटल समीक्षाओं के साथ भाव विश्लेषण अब जब आपने डेटासेट को विस्तार से देखा है, तो समय आ गया है कि कॉलम्स को फ़िल्टर करें और फिर डेटासेट पर NLP तकनीकों का उपयोग करके होटलों के बारे में नई जानकारी प्राप्त करें। diff --git a/translations/hi/6-NLP/5-Hotel-Reviews-2/assignment.md b/translations/hi/6-NLP/5-Hotel-Reviews-2/assignment.md index f638997bc..7ee8c0615 100644 --- a/translations/hi/6-NLP/5-Hotel-Reviews-2/assignment.md +++ b/translations/hi/6-NLP/5-Hotel-Reviews-2/assignment.md @@ -1,12 +1,3 @@ - # एक अलग डेटा सेट आज़माएं ## निर्देश diff --git a/translations/hi/6-NLP/5-Hotel-Reviews-2/solution/Julia/README.md b/translations/hi/6-NLP/5-Hotel-Reviews-2/solution/Julia/README.md index 5636c5da7..f5b86aaa6 100644 --- a/translations/hi/6-NLP/5-Hotel-Reviews-2/solution/Julia/README.md +++ b/translations/hi/6-NLP/5-Hotel-Reviews-2/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/6-NLP/5-Hotel-Reviews-2/solution/R/README.md b/translations/hi/6-NLP/5-Hotel-Reviews-2/solution/R/README.md index 5209a4e26..f5b86aaa6 100644 --- a/translations/hi/6-NLP/5-Hotel-Reviews-2/solution/R/README.md +++ b/translations/hi/6-NLP/5-Hotel-Reviews-2/solution/R/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/6-NLP/README.md b/translations/hi/6-NLP/README.md index 36b0a2fd6..1889e139e 100644 --- a/translations/hi/6-NLP/README.md +++ b/translations/hi/6-NLP/README.md @@ -1,12 +1,3 @@ - # प्राकृतिक भाषा प्रसंस्करण के साथ शुरुआत प्राकृतिक भाषा प्रसंस्करण (NLP) एक कंप्यूटर प्रोग्राम की क्षमता है जो मानव भाषा को समझता है, जैसा कि इसे बोला और लिखा जाता है -- इसे प्राकृतिक भाषा कहा जाता है। यह कृत्रिम बुद्धिमत्ता (AI) का एक घटक है। NLP पिछले 50 वर्षों से अस्तित्व में है और इसकी जड़ें भाषाविज्ञान के क्षेत्र में हैं। पूरा क्षेत्र मशीनों को मानव भाषा को समझने और संसाधित करने में मदद करने पर केंद्रित है। इसका उपयोग फिर वर्तनी जांच या मशीन अनुवाद जैसे कार्यों को करने के लिए किया जा सकता है। इसका कई क्षेत्रों में वास्तविक दुनिया में उपयोग होता है, जैसे चिकित्सा अनुसंधान, सर्च इंजन और व्यापार खुफिया। diff --git a/translations/hi/6-NLP/data/README.md b/translations/hi/6-NLP/data/README.md index 124f14bbc..6acad2ade 100644 --- a/translations/hi/6-NLP/data/README.md +++ b/translations/hi/6-NLP/data/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/7-TimeSeries/1-Introduction/README.md b/translations/hi/7-TimeSeries/1-Introduction/README.md index 1281e15ad..4a28f4c42 100644 --- a/translations/hi/7-TimeSeries/1-Introduction/README.md +++ b/translations/hi/7-TimeSeries/1-Introduction/README.md @@ -1,12 +1,3 @@ - # समय श्रृंखला पूर्वानुमान का परिचय ![समय श्रृंखला का स्केच नोट में सारांश](../../../../sketchnotes/ml-timeseries.png) diff --git a/translations/hi/7-TimeSeries/1-Introduction/assignment.md b/translations/hi/7-TimeSeries/1-Introduction/assignment.md index 772b9ad57..19624c174 100644 --- a/translations/hi/7-TimeSeries/1-Introduction/assignment.md +++ b/translations/hi/7-TimeSeries/1-Introduction/assignment.md @@ -1,12 +1,3 @@ - # कुछ और समय श्रृंखला का विज़ुअलाइज़ेशन करें ## निर्देश diff --git a/translations/hi/7-TimeSeries/1-Introduction/solution/Julia/README.md b/translations/hi/7-TimeSeries/1-Introduction/solution/Julia/README.md index 44df0a34c..92287c46f 100644 --- a/translations/hi/7-TimeSeries/1-Introduction/solution/Julia/README.md +++ b/translations/hi/7-TimeSeries/1-Introduction/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/7-TimeSeries/1-Introduction/solution/R/README.md b/translations/hi/7-TimeSeries/1-Introduction/solution/R/README.md index 0a972cc5d..6d7a7d13a 100644 --- a/translations/hi/7-TimeSeries/1-Introduction/solution/R/README.md +++ b/translations/hi/7-TimeSeries/1-Introduction/solution/R/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/7-TimeSeries/2-ARIMA/README.md b/translations/hi/7-TimeSeries/2-ARIMA/README.md index 2124150b9..1646c6b03 100644 --- a/translations/hi/7-TimeSeries/2-ARIMA/README.md +++ b/translations/hi/7-TimeSeries/2-ARIMA/README.md @@ -1,12 +1,3 @@ - # ARIMA के साथ समय श्रृंखला पूर्वानुमान पिछले पाठ में, आपने समय श्रृंखला पूर्वानुमान के बारे में थोड़ा सीखा और एक डेटा सेट लोड किया जो एक समय अवधि के दौरान विद्युत भार में उतार-चढ़ाव दिखाता है। diff --git a/translations/hi/7-TimeSeries/2-ARIMA/assignment.md b/translations/hi/7-TimeSeries/2-ARIMA/assignment.md index 2dbcbd7a8..1b6fa70bd 100644 --- a/translations/hi/7-TimeSeries/2-ARIMA/assignment.md +++ b/translations/hi/7-TimeSeries/2-ARIMA/assignment.md @@ -1,12 +1,3 @@ - # एक नया ARIMA मॉडल ## निर्देश diff --git a/translations/hi/7-TimeSeries/2-ARIMA/solution/Julia/README.md b/translations/hi/7-TimeSeries/2-ARIMA/solution/Julia/README.md index efcbdc440..92287c46f 100644 --- a/translations/hi/7-TimeSeries/2-ARIMA/solution/Julia/README.md +++ b/translations/hi/7-TimeSeries/2-ARIMA/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/7-TimeSeries/2-ARIMA/solution/R/README.md b/translations/hi/7-TimeSeries/2-ARIMA/solution/R/README.md index 8ed7102a6..7cc240ee9 100644 --- a/translations/hi/7-TimeSeries/2-ARIMA/solution/R/README.md +++ b/translations/hi/7-TimeSeries/2-ARIMA/solution/R/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/7-TimeSeries/3-SVR/README.md b/translations/hi/7-TimeSeries/3-SVR/README.md index f8909202c..4119aa5ce 100644 --- a/translations/hi/7-TimeSeries/3-SVR/README.md +++ b/translations/hi/7-TimeSeries/3-SVR/README.md @@ -1,12 +1,3 @@ - # सपोर्ट वेक्टर रेग्रेसर के साथ टाइम सीरीज़ फोरकास्टिंग पिछले पाठ में, आपने ARIMA मॉडल का उपयोग करके टाइम सीरीज़ प्रेडिक्शन करना सीखा। अब आप सपोर्ट वेक्टर रेग्रेसर मॉडल पर ध्यान देंगे, जो एक रेग्रेशन मॉडल है और निरंतर डेटा की भविष्यवाणी करने के लिए उपयोग किया जाता है। diff --git a/translations/hi/7-TimeSeries/3-SVR/assignment.md b/translations/hi/7-TimeSeries/3-SVR/assignment.md index 67d165d25..694d14eaa 100644 --- a/translations/hi/7-TimeSeries/3-SVR/assignment.md +++ b/translations/hi/7-TimeSeries/3-SVR/assignment.md @@ -1,12 +1,3 @@ - # एक नया SVR मॉडल ## निर्देश [^1] diff --git a/translations/hi/7-TimeSeries/README.md b/translations/hi/7-TimeSeries/README.md index 0436baea2..081a65c03 100644 --- a/translations/hi/7-TimeSeries/README.md +++ b/translations/hi/7-TimeSeries/README.md @@ -1,12 +1,3 @@ - # समय श्रृंखला पूर्वानुमान का परिचय समय श्रृंखला पूर्वानुमान क्या है? यह अतीत के रुझानों का विश्लेषण करके भविष्य की घटनाओं की भविष्यवाणी करने के बारे में है। diff --git a/translations/hi/8-Reinforcement/1-QLearning/README.md b/translations/hi/8-Reinforcement/1-QLearning/README.md index 05b4b7e52..6d7cfa9a7 100644 --- a/translations/hi/8-Reinforcement/1-QLearning/README.md +++ b/translations/hi/8-Reinforcement/1-QLearning/README.md @@ -1,12 +1,3 @@ - # परिचय: रिइंफोर्समेंट लर्निंग और Q-लर्निंग ![मशीन लर्निंग में रिइंफोर्समेंट का सारांश एक स्केच नोट में](../../../../sketchnotes/ml-reinforcement.png) diff --git a/translations/hi/8-Reinforcement/1-QLearning/assignment.md b/translations/hi/8-Reinforcement/1-QLearning/assignment.md index b2d185436..4e05e2612 100644 --- a/translations/hi/8-Reinforcement/1-QLearning/assignment.md +++ b/translations/hi/8-Reinforcement/1-QLearning/assignment.md @@ -1,12 +1,3 @@ - # एक अधिक यथार्थवादी दुनिया हमारी स्थिति में, पीटर लगभग बिना थके या भूखे हुए घूमने में सक्षम था। एक अधिक यथार्थवादी दुनिया में, उसे समय-समय पर बैठकर आराम करना होगा और खुद को भोजन देना होगा। चलिए हमारी दुनिया को अधिक यथार्थवादी बनाते हैं, निम्नलिखित नियम लागू करके: diff --git a/translations/hi/8-Reinforcement/1-QLearning/solution/Julia/README.md b/translations/hi/8-Reinforcement/1-QLearning/solution/Julia/README.md index d50c6d1a9..92287c46f 100644 --- a/translations/hi/8-Reinforcement/1-QLearning/solution/Julia/README.md +++ b/translations/hi/8-Reinforcement/1-QLearning/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/8-Reinforcement/1-QLearning/solution/R/README.md b/translations/hi/8-Reinforcement/1-QLearning/solution/R/README.md index 773b487b2..f683916b1 100644 --- a/translations/hi/8-Reinforcement/1-QLearning/solution/R/README.md +++ b/translations/hi/8-Reinforcement/1-QLearning/solution/R/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/8-Reinforcement/2-Gym/README.md b/translations/hi/8-Reinforcement/2-Gym/README.md index 51470de2f..b5c4b3bb5 100644 --- a/translations/hi/8-Reinforcement/2-Gym/README.md +++ b/translations/hi/8-Reinforcement/2-Gym/README.md @@ -1,12 +1,3 @@ - ## आवश्यकताएँ इस पाठ में, हम **OpenAI Gym** नामक एक लाइब्रेरी का उपयोग करेंगे जो विभिन्न **पर्यावरणों** को सिमुलेट करती है। आप इस पाठ का कोड स्थानीय रूप से (जैसे Visual Studio Code से) चला सकते हैं, जिसमें सिमुलेशन एक नई विंडो में खुलेगा। ऑनलाइन कोड चलाते समय, आपको कोड में कुछ बदलाव करने की आवश्यकता हो सकती है, जैसा कि [यहां](https://towardsdatascience.com/rendering-openai-gym-envs-on-binder-and-google-colab-536f99391cc7) वर्णित है। diff --git a/translations/hi/8-Reinforcement/2-Gym/assignment.md b/translations/hi/8-Reinforcement/2-Gym/assignment.md index c62219ea7..8d899bb98 100644 --- a/translations/hi/8-Reinforcement/2-Gym/assignment.md +++ b/translations/hi/8-Reinforcement/2-Gym/assignment.md @@ -1,12 +1,3 @@ - # माउंटेन कार को प्रशिक्षित करें [OpenAI Gym](http://gym.openai.com) को इस तरह से डिज़ाइन किया गया है कि सभी वातावरण एक ही API प्रदान करते हैं - जैसे कि वही विधियां `reset`, `step` और `render`, और **क्रिया स्थान** और **अवलोकन स्थान** की समान अमूर्तताएं। इसलिए, यह संभव होना चाहिए कि एक ही सुदृढीकरण शिक्षण एल्गोरिदम को न्यूनतम कोड परिवर्तनों के साथ विभिन्न वातावरणों में अनुकूलित किया जा सके। diff --git a/translations/hi/8-Reinforcement/2-Gym/solution/Julia/README.md b/translations/hi/8-Reinforcement/2-Gym/solution/Julia/README.md index 42f4219d2..f5b86aaa6 100644 --- a/translations/hi/8-Reinforcement/2-Gym/solution/Julia/README.md +++ b/translations/hi/8-Reinforcement/2-Gym/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/8-Reinforcement/2-Gym/solution/R/README.md b/translations/hi/8-Reinforcement/2-Gym/solution/R/README.md index 837070572..06bdc5c40 100644 --- a/translations/hi/8-Reinforcement/2-Gym/solution/R/README.md +++ b/translations/hi/8-Reinforcement/2-Gym/solution/R/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/hi/8-Reinforcement/README.md b/translations/hi/8-Reinforcement/README.md index 6bf1e557b..30eb3172e 100644 --- a/translations/hi/8-Reinforcement/README.md +++ b/translations/hi/8-Reinforcement/README.md @@ -1,12 +1,3 @@ - # परिचय: रिइनफोर्समेंट लर्निंग रिइनफोर्समेंट लर्निंग (RL) को मशीन लर्निंग के तीन मुख्य दृष्टिकोणों में से एक माना जाता है, अन्य दो हैं सुपरवाइज्ड लर्निंग और अनसुपरवाइज्ड लर्निंग। RL निर्णय लेने पर आधारित है: सही निर्णय लेना या कम से कम उनसे सीखना। diff --git a/translations/hi/9-Real-World/1-Applications/README.md b/translations/hi/9-Real-World/1-Applications/README.md index f952d70d5..06aa1ef77 100644 --- a/translations/hi/9-Real-World/1-Applications/README.md +++ b/translations/hi/9-Real-World/1-Applications/README.md @@ -1,12 +1,3 @@ - # पोस्टस्क्रिप्ट: वास्तविक दुनिया में मशीन लर्निंग ![वास्तविक दुनिया में मशीन लर्निंग का सारांश एक स्केच नोट में](../../../../sketchnotes/ml-realworld.png) diff --git a/translations/hi/9-Real-World/1-Applications/assignment.md b/translations/hi/9-Real-World/1-Applications/assignment.md index 7de52ad57..ca04f81c8 100644 --- a/translations/hi/9-Real-World/1-Applications/assignment.md +++ b/translations/hi/9-Real-World/1-Applications/assignment.md @@ -1,12 +1,3 @@ - # एक एमएल स्कैवेंजर हंट ## निर्देश diff --git a/translations/hi/9-Real-World/2-Debugging-ML-Models/README.md b/translations/hi/9-Real-World/2-Debugging-ML-Models/README.md index a59f24930..a069c3c84 100644 --- a/translations/hi/9-Real-World/2-Debugging-ML-Models/README.md +++ b/translations/hi/9-Real-World/2-Debugging-ML-Models/README.md @@ -1,12 +1,3 @@ - # पोस्टस्क्रिप्ट: मशीन लर्निंग में मॉडल डिबगिंग का जिम्मेदार AI डैशबोर्ड घटकों के साथ उपयोग ## [प्री-लेक्चर क्विज़](https://ff-quizzes.netlify.app/en/ml/) diff --git a/translations/hi/9-Real-World/2-Debugging-ML-Models/assignment.md b/translations/hi/9-Real-World/2-Debugging-ML-Models/assignment.md index 842a78bad..cd0d4e86f 100644 --- a/translations/hi/9-Real-World/2-Debugging-ML-Models/assignment.md +++ b/translations/hi/9-Real-World/2-Debugging-ML-Models/assignment.md @@ -1,12 +1,3 @@ - # जिम्मेदार AI (RAI) डैशबोर्ड का अन्वेषण करें ## निर्देश diff --git a/translations/hi/9-Real-World/README.md b/translations/hi/9-Real-World/README.md index 9180ae988..f4d4f9329 100644 --- a/translations/hi/9-Real-World/README.md +++ b/translations/hi/9-Real-World/README.md @@ -1,12 +1,3 @@ - # पोस्टस्क्रिप्ट: क्लासिक मशीन लर्निंग के वास्तविक दुनिया में उपयोग इस पाठ्यक्रम के इस भाग में, आपको क्लासिकल मशीन लर्निंग के कुछ वास्तविक दुनिया में उपयोगों से परिचित कराया जाएगा। हमने इंटरनेट पर खोजबीन की है और ऐसे श्वेतपत्र और लेख ढूंढे हैं जो इन रणनीतियों का उपयोग करते हैं, न्यूरल नेटवर्क, डीप लर्निंग और एआई से यथासंभव बचते हुए। जानें कि व्यवसाय प्रणालियों, पारिस्थितिक अनुप्रयोगों, वित्त, कला और संस्कृति, और अन्य क्षेत्रों में मशीन लर्निंग का उपयोग कैसे किया जाता है। diff --git a/translations/hi/AGENTS.md b/translations/hi/AGENTS.md index 2b82d843a..5448c6eee 100644 --- a/translations/hi/AGENTS.md +++ b/translations/hi/AGENTS.md @@ -1,12 +1,3 @@ - # AGENTS.md ## परियोजना का अवलोकन diff --git a/translations/hi/CODE_OF_CONDUCT.md b/translations/hi/CODE_OF_CONDUCT.md index c39a1aa0e..c5831c917 100644 --- a/translations/hi/CODE_OF_CONDUCT.md +++ b/translations/hi/CODE_OF_CONDUCT.md @@ -1,12 +1,3 @@ - # Microsoft ओपन सोर्स आचार संहिता इस प्रोजेक्ट ने [Microsoft ओपन सोर्स आचार संहिता](https://opensource.microsoft.com/codeofconduct/) को अपनाया है। diff --git a/translations/hi/CONTRIBUTING.md b/translations/hi/CONTRIBUTING.md index ee6b66003..199dbcdad 100644 --- a/translations/hi/CONTRIBUTING.md +++ b/translations/hi/CONTRIBUTING.md @@ -1,12 +1,3 @@ - # योगदान यह प्रोजेक्ट योगदान और सुझावों का स्वागत करता है। अधिकांश योगदानों के लिए आपको एक Contributor License Agreement (CLA) से सहमत होना होगा, जिसमें यह घोषित किया जाता है कि आपके पास अधिकार हैं और आप हमें अपने योगदान का उपयोग करने का अधिकार प्रदान करते हैं। विवरण के लिए, https://cla.microsoft.com पर जाएं। diff --git a/translations/hi/README.md b/translations/hi/README.md index 8a03e53d6..5527790a2 100644 --- a/translations/hi/README.md +++ b/translations/hi/README.md @@ -1,96 +1,76 @@ - -[![GitHub license](https://img.shields.io/github/license/microsoft/ML-For-Beginners.svg)](https://github.com/microsoft/ML-For-Beginners/blob/master/LICENSE) -[![GitHub contributors](https://img.shields.io/github/contributors/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/graphs/contributors/) -[![GitHub issues](https://img.shields.io/github/issues/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/issues/) -[![GitHub pull-requests](https://img.shields.io/github/issues-pr/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/pulls/) -[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com) - -[![GitHub watchers](https://img.shields.io/github/watchers/microsoft/ML-For-Beginners.svg?style=social&label=Watch)](https://GitHub.com/microsoft/ML-For-Beginners/watchers/) -[![GitHub forks](https://img.shields.io/github/forks/microsoft/ML-For-Beginners.svg?style=social&label=Fork)](https://GitHub.com/microsoft/ML-For-Beginners/network/) -[![GitHub stars](https://img.shields.io/github/stars/microsoft/ML-For-Beginners.svg?style=social&label=Star)](https://GitHub.com/microsoft/ML-For-Beginners/stargazers/) - -### 🌐 मल्टी-भाषा समर्थन - -#### गिटहब एक्शन के माध्यम से समर्थित (स्वचालित और हमेशा अद्यतन) +### 🌐 बहुभाषी समर्थन + +#### GitHub एक्शन के माध्यम से समर्थित (स्वचालित और हमेशा अद्यतित) -[Arabic](../ar/README.md) | [Bengali](../bn/README.md) | [Bulgarian](../bg/README.md) | [Burmese (Myanmar)](../my/README.md) | [Chinese (Simplified)](../zh/README.md) | [Chinese (Traditional, Hong Kong)](../hk/README.md) | [Chinese (Traditional, Macau)](../mo/README.md) | [Chinese (Traditional, Taiwan)](../tw/README.md) | [Croatian](../hr/README.md) | [Czech](../cs/README.md) | [Danish](../da/README.md) | [Dutch](../nl/README.md) | [Estonian](../et/README.md) | [Finnish](../fi/README.md) | [French](../fr/README.md) | [German](../de/README.md) | [Greek](../el/README.md) | [Hebrew](../he/README.md) | [Hindi](./README.md) | [Hungarian](../hu/README.md) | [Indonesian](../id/README.md) | [Italian](../it/README.md) | [Japanese](../ja/README.md) | [Kannada](../kn/README.md) | [Korean](../ko/README.md) | [Lithuanian](../lt/README.md) | [Malay](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepali](../ne/README.md) | [Nigerian Pidgin](../pcm/README.md) | [Norwegian](../no/README.md) | [Persian (Farsi)](../fa/README.md) | [Polish](../pl/README.md) | [Portuguese (Brazil)](../br/README.md) | [Portuguese (Portugal)](../pt/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Romanian](../ro/README.md) | [Russian](../ru/README.md) | [Serbian (Cyrillic)](../sr/README.md) | [Slovak](../sk/README.md) | [Slovenian](../sl/README.md) | [Spanish](../es/README.md) | [Swahili](../sw/README.md) | [Swedish](../sv/README.md) | [Tagalog (Filipino)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugu](../te/README.md) | [Thai](../th/README.md) | [Turkish](../tr/README.md) | [Ukrainian](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnamese](../vi/README.md) +[Arabic](../ar/README.md) | [Bengali](../bn/README.md) | [Bulgarian](../bg/README.md) | [Burmese (Myanmar)](../my/README.md) | [Chinese (Simplified)](../zh-CN/README.md) | [Chinese (Traditional, Hong Kong)](../zh-HK/README.md) | [Chinese (Traditional, Macau)](../zh-MO/README.md) | [Chinese (Traditional, Taiwan)](../zh-TW/README.md) | [Croatian](../hr/README.md) | [Czech](../cs/README.md) | [Danish](../da/README.md) | [Dutch](../nl/README.md) | [Estonian](../et/README.md) | [Finnish](../fi/README.md) | [French](../fr/README.md) | [German](../de/README.md) | [Greek](../el/README.md) | [Hebrew](../he/README.md) | [Hindi](./README.md) | [Hungarian](../hu/README.md) | [Indonesian](../id/README.md) | [Italian](../it/README.md) | [Japanese](../ja/README.md) | [Kannada](../kn/README.md) | [Korean](../ko/README.md) | [Lithuanian](../lt/README.md) | [Malay](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepali](../ne/README.md) | [Nigerian Pidgin](../pcm/README.md) | [Norwegian](../no/README.md) | [Persian (Farsi)](../fa/README.md) | [Polish](../pl/README.md) | [Portuguese (Brazil)](../pt-BR/README.md) | [Portuguese (Portugal)](../pt-PT/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Romanian](../ro/README.md) | [Russian](../ru/README.md) | [Serbian (Cyrillic)](../sr/README.md) | [Slovak](../sk/README.md) | [Slovenian](../sl/README.md) | [Spanish](../es/README.md) | [Swahili](../sw/README.md) | [Swedish](../sv/README.md) | [Tagalog (Filipino)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugu](../te/README.md) | [Thai](../th/README.md) | [Turkish](../tr/README.md) | [Ukrainian](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnamese](../vi/README.md) -> **स्थानीय रूप से क्लोन करना पसंद करते हैं?** +> **स्थानीय रूप से क्लोन करना पसंद करें?** -> इस रिपॉज़िटरी में 50+ भाषा अनुवाद शामिल हैं जो डाउनलोड आकार को काफी बढ़ाते हैं। बिना अनुवादों के क्लोन करने के लिए, sparse checkout का उपयोग करें: +> यह रिपॉजिटरी 50+ भाषा अनुवाद शामिल करता है जो डाउनलोड आकार को काफी बढ़ाता है। बिना अनुवादों के क्लोन करने के लिए sparse checkout का उपयोग करें: > ```bash > git clone --filter=blob:none --sparse https://github.com/microsoft/ML-For-Beginners.git > cd ML-For-Beginners > git sparse-checkout set --no-cone '/*' '!translations' '!translated_images' > ``` -> इससे आपको कोर्स पूरा करने के लिए आवश्यक सबकुछ मिलता है, डाउनलोड तेजी से होता है। +> इससे आपको कोर्स पूरा करने के लिए आवश्यक सब कुछ बहुत तेज़ डाउनलोड के साथ मिलेगा। #### हमारे समुदाय में शामिल हों [![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -हमारे पास Discord पर AI के साथ सीखने की एक श्रृंखला चल रही है, अधिक जानने और हमारे साथ जुड़ने के लिए [Learn with AI Series](https://aka.ms/learnwithai/discord) पर जाएं, जो 18 - 30 सितंबर, 2025 को आयोजित होगी। आपको डेटा साइंस के लिए GitHub Copilot का उपयोग करने के टिप्स और ट्रिक्स मिलेंगे। +हमारे पास AI के साथ सीखने की एक श्रृंखला डिस्कॉर्ड पर चल रही है, अधिक जानने और 18 - 30 सितंबर, 2025 को [Learn with AI Series](https://aka.ms/learnwithai/discord) पर हमारे साथ जुड़ें। आप डेटा साइंस के लिए GitHub Copilot के उपयोग के टिप्स और ट्रिक्स प्राप्त करेंगे। -![Learn with AI series](../../../../translated_images/hi/3.9b58fd8d6c373c20.webp) +![Learn with AI series](../../translated_images/hi/3.9b58fd8d6c373c20.webp) -# शुरुआती लोगों के लिए मशीन लर्निंग - एक पाठ्यक्रम +# शुरुआती के लिए मशीन लर्निंग - एक पाठ्यक्रम -> 🌍 विश्व की संस्कृतियों के माध्यम से मशीन लर्निंग का अन्वेषण करते हुए दुनिया भर की यात्रा करें 🌍 +> 🌍 जैसे-जैसे हम मशीन लर्निंग का पता लगाते हैं, दुनिया भर की संस्कृतियों के माध्यम से यात्रा करें 🌍 -Microsoft के Cloud Advocates एक 12-सप्ताह, 26-पाठ का पाठ्यक्रम प्रस्तुत कर रहे हैं जो पूरी तरह से **मशीन लर्निंग** के बारे में है। इस पाठ्यक्रम में, आप उन चीज़ों के बारे में सीखेंगे जिन्हें कभी-कभी **क्लासिक मशीन लर्निंग** कहा जाता है, जो मुख्य रूप से Scikit-learn लाइब्रेरी का उपयोग करता है और डीप लर्निंग से बचता है, जिसे हमारे [AI for Beginners' curriculum](https://aka.ms/ai4beginners) में कवर किया गया है। इन पाठों को हमारे ['Data Science for Beginners' curriculum](https://aka.ms/ds4beginners) के साथ भी जोडें। +Microsoft के क्लाउड एडवोकेट खुशी से एक 12 सप्ताह, 26-पाठ्यक्रम प्रदान कर रहे हैं जो पूरी तरह से **मशीन लर्निंग** के बारे में है। इस पाठ्यक्रम में, आप जो कुछ कभी-कभी **क्लासिक मशीन लर्निंग** कहा जाता है, उसे सीखेंगे, जिसमें मुख्य रूप से स्किकिट-लर्न पुस्तकालय का उपयोग होता है और डीप लर्निंग से बचा जाता है, जो हमारे [AI for Beginners' curriculum](https://aka.ms/ai4beginners) में कवर किया गया है। इस पाठ्यक्रम के साथ हमारे ['डेटा साइंस फॉर बिगिनर्स' curriculum](https://aka.ms/ds4beginners) को भी जोड़ें! -दुनिया भर के डेटा पर इन क्लासिक तकनीकों को लागू करते हुए हमारे साथ विश्व भ्रमण करें। प्रत्येक पाठ में प्री-लेसन और पोस्ट-लेसन क्विज़, पाठपूर्ण निर्देश, समाधान, असाइनमेंट आदि शामिल हैं। हमारा प्रोजेक्ट-आधारित तरीका आपको निर्माण करते हुए सीखने की सुविधा देता है, जो नई स्किल्स को बेहतर ढंग से सीखने का प्रमाणित तरीका है। +हमारे साथ दुनिया भर की यात्रा करें क्योंकि हम इन क्लासिक तकनीकों को दुनिया के कई क्षेत्रों के डेटा पर लागू करते हैं। प्रत्येक पाठ में पूर्व और बाद के क्विज, पाठ पूरा करने के लिए लिखित निर्देश, एक समाधान, एक असाइनमेंट, और बहुत कुछ शामिल है। हमारा परियोजना-आधारित शिक्षण तरीका आपको निर्माण करते हुए सीखने की अनुमति देता है, जो नई कौशलों को 'टिकाने' का एक सिद्ध तरीका है। -**✍️ हमारे लेखकों को हार्दिक धन्यवाद** जेन लूपर, स्टीफन हाउल, फ्रांसेस्का लज्जेरी, तोमोमी इमुरा, कैसी ब्रेवियू, दिमित्री सॉश्निकोव, क्रिस नोऱिंग, अनिरбан मुखर्जी, ऑर्नेला आल्टुन्यन, रूथ यकुबु और एमी बॉयड +**✍️ हमारे लेखकों को हार्दिक धन्यवाद** जेन लूपर, स्टीफन हॉवेल, फ्रांसेस्का लाज्जेरी, टोमोमी इमुरा, कैसी ब्रेवियू, दिमित्री सोश्निकोव, क्रिस नोरेन, अनिर्बान मुखर्जी, ऑर्नेला अल्टुनयान, रूथ याकुबु और एमी बॉयड -**🎨 हमारे चित्रकारों को भी धन्यवाद** तोमोमी इमुरा, दासानी मडिपल्ली, और जेन लूपर +**🎨 हमारे इलस्ट्रेटर्स को भी धन्यवाद** टोमोमी इमुरा, दासनी मदीपल्ली, और जेन लूपर -**🙏 विशेष धन्यवाद 🙏 हमारे Microsoft Student Ambassador लेखकों, समीक्षकों और कंटेंट सहयोगियों को**, खासकर ऋषित डागली, मोहम्मद साकिब खान इनान, रोहन राज, अलेक्ज़ान्द्रु पेट्रेसकु, अभिषेक जायसवाल, नवरीन तबस्सुम, इओन सामइला, और स्निग्धा अग्रवाल +**🙏 विशेष धन्यवाद 🙏 हमारे Microsoft Student Ambassador लेखकों, समीक्षकों, और सामग्री योगदानकर्ताओं को**, विशेष रूप से ऋषित डागली, मुहम्मद साकिब खान इनान, रोहन राज, अलेक्जेंडरु पेट्रेस्कु, अभिषेक जयसवाल, नवरिन तबस्सुम, इवान समुइला, और स्निग्धा अगरवाल -**🤩 Microsoft Student Ambassadors एरिक वांजाउ, जसलीन सोनधी, और विदुषी गुप्ता को हमारे आर लेसंस के लिए अतिरिक्त आभार!** +**🤩 अतिरिक्त कृतज्ञता Microsoft Student Ambassadors एरिक वांजाउ, जसलीन संधि, और विदुषी गुप्ता को हमारे R पाठों के लिए!** -# शुरू करना +# शुरुआत करना इन चरणों का पालन करें: -1. **रिपॉज़िटरी को फोर्क करें**: इस पृष्ठ के ऊपर-दाएँ कोने में "Fork" बटन पर क्लिक करें। -2. **रिपॉज़िटरी को क्लोन करें**: `git clone https://github.com/microsoft/ML-For-Beginners.git` - -> [इस कोर्स के लिए हमारे Microsoft Learn संग्रह में सभी अतिरिक्त संसाधन खोजें](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) +1. **रिपॉजिटरी को फोर्क करें**: इस पेज के शीर्ष-दाएँ कोने में "Fork" बटन पर क्लिक करें। +2. **रिपॉजिटरी क्लोन करें**: `git clone https://github.com/microsoft/ML-For-Beginners.git` -> 🔧 **मदद चाहिए?** इंस्टॉलेशन, सेटअप, और पाठ चलाने से संबंधित सामान्य समस्याओं के समाधान के लिए हमारे [Troubleshooting Guide](TROUBLESHOOTING.md) देखें। +> [इस कोर्स के लिए सभी अतिरिक्त संसाधन हमारे Microsoft Learn संग्रह में पाएँ](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) +> 🔧 **मदद चाहिए?** इंस्टॉलेशन, सेटअप, और पाठ चलाने में सामान्य समस्याओं के समाधान के लिए हमारे [Troubleshooting Guide](TROUBLESHOOTING.md) को देखें। -**[छात्रों](https://aka.ms/student-page)**, इस पाठ्यक्रम का उपयोग करने के लिए, पूरे रिपॉज़िटरी को अपने GitHub अकाउंट पर फोर्क करें और अभ्यास अकेले या समूह में करें: +**[छात्रों](https://aka.ms/student-page)**, इस पाठ्यक्रम का उपयोग करने के लिए, पूरे रेपो को अपने GitHub खाते में फोर्क करें और व्यायाम अपनी तरफ से या समूह के साथ पूरे करें: -- प्री-लेक्चर क्विज़ से शुरू करें। +- प्री-लेक्चर क्विज से शुरू करें। - व्याख्यान पढ़ें और गतिविधियाँ पूरी करें, प्रत्येक ज्ञान जांच पर रुके और विचार करें। -- समाधान कोड चलाने के बजाय पाठ समझकर परियोजनाएँ बनाने का प्रयास करें; हालांकि यह कोड प्रत्येक प्रोजेक्ट-आधारित पाठ में `/solution` फ़ोल्डर में उपलब्ध है। -- पोस्ट-लेक्चर क्विज़ लें। -- चैलेंज पूरा करें। -- असाइनमेंट पूरा करें। -- एक लेसन समूह पूरा करने के बाद, [डिस्कशन बोर्ड](https://github.com/microsoft/ML-For-Beginners/discussions) पर जाएं और उपयुक्त PAT रुब्रिक भरकर "जोर से सीखें"। 'PAT' एक प्रोग्रेस असेसमेंट टूल है जो आपकी प्रगति को ट्रैक करता है। आप अन्य PAT पर प्रतिक्रिया भी दे सकते हैं ताकि हम साथ में सीख सकें। +- पाठों को समझकर परियोजनाएँ बनाने का प्रयास करें बजाय समाधान कोड चलाने के; हालांकि वह कोड प्रत्येक परियोजना-केंद्रित पाठ में `/solution` फ़ोल्डर्स में उपलब्ध है। +- पोस्ट-लेक्चर क्विज लें। +- चुनौती पूरी करें। +- असाइनमेंट पूरी करें। +- एक पाठ समूह पूरा करने के बाद, [चर्चा बोर्ड](https://github.com/microsoft/ML-For-Beginners/discussions) पर जाएं और उपयुक्त PAT रूपरेखा भरकर "ज़ोरदार रूप से सीखें"। 'PAT' एक प्रोग्रेस असेसमेंट टूल है जो आपकी सीख को आगे बढ़ाने के लिए एक रूपरेखा है। आप अन्य PATs पर प्रतिक्रिया भी दे सकते हैं ताकि हम साथ मिलकर सीख सकें। -> आगे के अध्ययन के लिए, हम इन [Microsoft Learn](https://docs.microsoft.com/en-us/users/jenlooper-2911/collections/k7o7tg1gp306q4?WT.mc_id=academic-77952-leestott) मॉड्यूल और लर्निंग पाथ का अनुसरण करने की सलाह देते हैं। +> आगे अध्ययन के लिए, हम इन [Microsoft Learn](https://docs.microsoft.com/en-us/users/jenlooper-2911/collections/k7o7tg1gp306q4?WT.mc_id=academic-77952-leestott) मॉड्यूल और लर्निंग पथों का पालन करने की सलाह देते हैं। -**शिक्षक वर्ग**, हमने [कुछ सुझाव](for-teachers.md) शामिल किए हैं कि इस पाठ्यक्रम का उपयोग कैसे करें। +**शिक्षकों**, हमने इस पाठ्यक्रम का उपयोग करने के कुछ सुझाव [यहाँ शामिल किए हैं](for-teachers.md)। --- ## वीडियो वॉकथ्रू -कुछ पाठ छोटे वीडियो के रूप में उपलब्ध हैं। आप इन्हें सभी पाठों में इन-लाइन पा सकते हैं, या Microsoft Developer YouTube चैनल पर [ML for Beginners प्लेलिस्ट](https://aka.ms/ml-beginners-videos) पर नीचे दी गई छवि पर क्लिक करके देख सकते हैं। +कुछ पाठ अल्पकालिक वीडियो के रूप में उपलब्ध हैं। आप इन्हें पाठों में इन-लाइन पा सकते हैं, या Microsoft Developer YouTube चैनल पर [ML for Beginners प्लेलिस्ट](https://aka.ms/ml-beginners-videos) में नीचे की छवि पर क्लिक करके देख सकते हैं। -[![ML for beginners banner](../../../../translated_images/hi/ml-for-beginners-video-banner.63f694a100034bc6.webp)](https://aka.ms/ml-beginners-videos) +[![ML for beginners banner](../../translated_images/hi/ml-for-beginners-video-banner.63f694a100034bc6.webp)](https://aka.ms/ml-beginners-videos) --- @@ -100,79 +80,79 @@ Microsoft के Cloud Advocates एक 12-सप्ताह, 26-पाठ क **Gif द्वारा** [Mohit Jaisal](https://linkedin.com/in/mohitjaisal) -> 🎥 परियोजना और इसे बनाने वाले लोगों के बारे में वीडियो के लिए ऊपर दी गई छवि पर क्लिक करें! +> 🎥 परियोजना और इसे बनाने वाले लोगों के बारे में वीडियो देखने के लिए ऊपर की छवि पर क्लिक करें! --- ## शिक्षण पद्धति -इस पाठ्यक्रम को बनाते समय हमने दो शिक्षण सिद्धांत चुने हैं: यह सुनिश्चित करना कि यह हैंड्स-ऑन **प्रोजेक्ट-आधारित** हो और इसमें **बार-बार क्विज़** शामिल हों। इसके अलावा, इस पाठ्यक्रम में एक सामान्य **थीम** है जो इसे एकरूपता प्रदान करता है। +इस पाठ्यक्रम को बनाते समय हमने दो शिक्षण सिद्धांत चुने हैं: इसे हाथों-हाथ **परियोजना-आधारित** बनाना और इसमें **अक्सर क्विज़ शामिल** करना। इसके अलावा, इस पाठ्यक्रम का एक सामान्य **थीम** है जिससे इसे सामंजस्य मिलता है। -सामग्री को प्रोजेक्ट्स से जोड़कर, प्रक्रिया छात्रों के लिए अधिक आकर्षक हो जाती है और अवधारणाओं को बेहतर बनाए रखती है। एक कक्षा से पहले एक कम-जोखिम वाला क्विज़ छात्र के सीखने के इरादे को सेट करता है, जबकि कक्षा के बाद दूसरा क्विज़ और अच्छे से अवधारणाओं को स्थिर करता है। यह पाठ्यक्रम लचीला और मजेदार होने के लिए डिज़ाइन किया गया है और पूरे या आंशिक रूप से किया जा सकता है। परियोजनाएँ छोटी से शुरू होकर 12-सप्ताह के अंत तक जटिल हो जाती हैं। इस पाठ्यक्रम में मशीन लर्निंग के वास्तविक दुनिया के अनुप्रयोगों पर एक पोस्टस्क्रिप्ट भी शामिल है, जिसे अतिरिक्त क्रेडिट के रूप में या चर्चा के आधार के रूप में इस्तेमाल किया जा सकता है। +यह सुनिश्चित करके कि सामग्री परियोजनाओं के अनुरूप है, प्रक्रिया छात्रों के लिए अधिक आकर्षक बनती है और अवधारणाओं की पकड़ बढ़ेगी। इसके अलावा, क्लास से पहले एक कम-दांव वाला क्विज़ छात्र की एक विषय सीखने की इच्छा निर्धारित करता है, जबकि क्लास के बाद दूसरा क्विज़ और भी बेहतर पकड़ सुनिश्चित करता है। यह पाठ्यक्रम लचीला और मजेदार है और इसे पूरा या आंशिक रूप से लिया जा सकता है। परियोजनाएं छोटी शुरू होती हैं और 12 सप्ताह के चक्र के अंत तक धीरे-धीरे जटिल होती चली जाती हैं। यह पाठ्यक्रम मशीन लर्निंग के वास्तविक अनुप्रयोगों पर एक पश्चलिपि भी शामिल करता है, जिसे अतिरिक्त क्रेडिट या चर्चा के आधार के रूप में उपयोग किया जा सकता है। > हमारे [Code of Conduct](CODE_OF_CONDUCT.md), [Contributing](CONTRIBUTING.md), [Translation](TRANSLATIONS.md), और [Troubleshooting](TROUBLESHOOTING.md) दिशानिर्देश देखें। हम आपके रचनात्मक सुझावों का स्वागत करते हैं! ## प्रत्येक पाठ में शामिल हैं - वैकल्पिक स्केचनोट -- वैकल्पिक पूरक वीडियो -- वीडियो वॉकथ्रू (कुछ पाठों में ही) -- [प्री-लेक्चर वार्मअप क्विज़](https://ff-quizzes.netlify.app/en/ml/) +- वैकल्पिक सहायक वीडियो +- वीडियो वॉकथ्रू (कुछ पाठ केवल) +- [प्री-लेक्चर वार्मअप क्विज](https://ff-quizzes.netlify.app/en/ml/) - लिखित पाठ -- प्रोजेक्ट-आधारित पाठ के लिए, परियोजना बनाने के चरण-दर-चरण गाइड +- परियोजना-आधारित पाठों के लिए परियोजना बनाने के चरण-दर-चरण मार्गदर्शक - ज्ञान जांच - एक चुनौती -- पूरक अध्ययन सामग्री +- सहायक पठन सामग्री - असाइनमेंट -- [पोस्ट-लेक्चर क्विज़](https://ff-quizzes.netlify.app/en/ml/) - -> **भाषाओं के बारे में एक नोट**: ये पाठ मुख्य रूप से Python में लिखे गए हैं, लेकिन कई R में भी उपलब्ध हैं। R पाठ पूरा करने के लिए, `/solution` फ़ोल्डर में जाकर R पाठ खोजें। इनमें .rmd एक्सटेंशन होता है जो एक **R Markdown** फ़ाइल को दर्शाता है, जिसे सरलता से `कोड चंक` (R या अन्य भाषाओं के) और `YAML हेडर` (जो आउटपुट, जैसे PDF, को फ़ॉर्मैट करने का मार्गदर्शन करता है) का सम्मिलन कहा जा सकता है। इसलिए, यह डेटा साइंस के लिए एक आदर्श लेखक फ्रेमवर्क है क्योंकि यह आपको अपने कोड, उसके आउटपुट, और अपने विचारों को Markdown में लिखने की अनुमति देता है। इसके अलावा, R Markdown दस्तावेज़ों को PDF, HTML, या Word जैसे आउटपुट स्वरूपों में रेंडर किया जा सकता है। -> **क्विज़ के बारे में एक नोट**: सभी क्विज़ [Quiz App folder](../../quiz-app) में शामिल हैं, जिनमें प्रत्येक में तीन प्रश्नों वाले कुल 52 क्विज़ हैं। वे पाठों के भीतर लिंक किए गए हैं लेकिन क्विज़ ऐप को स्थानीय रूप से भी चलाया जा सकता है; स्थानीय रूप से होस्ट या Azure पर तैनात करने के निर्देश `quiz-app` फ़ोल्डर में देखें। - -| Lesson Number | Topic | Lesson Grouping | Learning Objectives | Linked Lesson | Author | -| :-----------: | :------------------------------------------------------------: | :-------------------------------------------------: | ------------------------------------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------: | -| 01 | मशीन लर्निंग का परिचय | [Introduction](1-Introduction/README.md) | मशीन लर्निंग के पीछे के मूलभूत सिद्धांतों को सीखें | [Lesson](1-Introduction/1-intro-to-ML/README.md) | मुहम्मद | -| 02 | मशीन लर्निंग का इतिहास | [Introduction](1-Introduction/README.md) | इस क्षेत्र की ऐतिहासिक पृष्ठभूमि को जानें | [Lesson](1-Introduction/2-history-of-ML/README.md) | जेन और एमी | -| 03 | निष्पक्षता और मशीन लर्निंग | [Introduction](1-Introduction/README.md) | मशीन लर्निंग मॉडल बनाने और लागू करने में जो महत्वपूर्ण दार्शनिक मुद्दें होते हैं उन्हें समझें | [Lesson](1-Introduction/3-fairness/README.md) | टोमोमी | -| 04 | मशीन लर्निंग के तकनीकियाँ | [Introduction](1-Introduction/README.md) | मशीन लर्निंग के शोधकर्ता कौन-कौन सी तकनीकें उपयोग करते हैं मॉडल बनाने के लिए? | [Lesson](1-Introduction/4-techniques-of-ML/README.md) | क्रिस और जेन | -| 05 | रिग्रेशन का परिचय | [Regression](2-Regression/README.md) | रिग्रेशन मॉडल के लिए Python और Scikit-learn के साथ शुरूआत करें | [Python](2-Regression/1-Tools/README.md) • [R](../../2-Regression/1-Tools/solution/R/lesson_1.html) | जेन • एरिक वांजाउ | -| 06 | उत्तर अमेरिका के कद्दू के दाम 🎃 | [Regression](2-Regression/README.md) | मशीन लर्निंग के लिए डेटा को visualize और साफ़ करें | [Python](2-Regression/2-Data/README.md) • [R](../../2-Regression/2-Data/solution/R/lesson_2.html) | जेन • एरिक वांजाउ | -| 07 | उत्तर अमेरिका के कद्दू के दाम 🎃 | [Regression](2-Regression/README.md) | रैखिक और बहुपद रिग्रेशन मॉडल बनाएं | [Python](2-Regression/3-Linear/README.md) • [R](../../2-Regression/3-Linear/solution/R/lesson_3.html) | जेन और द्मित्री • एरिक वांजाउ | -| 08 | उत्तर अमेरिका के कद्दू के दाम 🎃 | [Regression](2-Regression/README.md) | लॉजिस्टिक रिग्रेशन मॉडल बनाएं | [Python](2-Regression/4-Logistic/README.md) • [R](../../2-Regression/4-Logistic/solution/R/lesson_4.html) | जेन • एरिक वांजाउ | -| 09 | एक वेब ऐप 🔌 | [Web App](3-Web-App/README.md) | अपने प्रशिक्षित मॉडल का उपयोग करने के लिए वेब ऐप बनाएं | [Python](3-Web-App/1-Web-App/README.md) | जेन | -| 10 | वर्गीकरण का परिचय | [Classification](4-Classification/README.md) | अपने डेटा को साफ़ करें, तैयार करें और visualize करें; वर्गीकरण का परिचय | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | जेन और कैसी • एरिक वांजाउ | -| 11 | स्वादिष्ट एशियाई और भारतीय व्यंजनों 🍜 | [Classification](4-Classification/README.md) | वर्गीकरणकों का परिचय | [Python](4-Classification/2-Classifiers-1/README.md) • [R](../../4-Classification/2-Classifiers-1/solution/R/lesson_11.html) | जेन और कैसी • एरिक वांजाउ | -| 12 | स्वादिष्ट एशियाई और भारतीय व्यंजनों 🍜 | [Classification](4-Classification/README.md) | अधिक वर्गीकरणक | [Python](4-Classification/3-Classifiers-2/README.md) • [R](../../4-Classification/3-Classifiers-2/solution/R/lesson_12.html) | जेन और कैसी • एरिक वांजाउ | -| 13 | स्वादिष्ट एशियाई और भारतीय व्यंजनों 🍜 | [Classification](4-Classification/README.md) | अपने मॉडल का उपयोग कर एक recommender वेब ऐप बनाएं | [Python](4-Classification/4-Applied/README.md) | जेन | -| 14 | क्लस्टरिंग का परिचय | [Clustering](5-Clustering/README.md) | अपने डेटा को साफ़ करें, तैयार करें और visualize करें; क्लस्टरिंग का परिचय | [Python](5-Clustering/1-Visualize/README.md) • [R](../../5-Clustering/1-Visualize/solution/R/lesson_14.html) | जेन • एरिक वांजाउ | -| 15 | नाइजीरियाई संगीत रुचियों का अन्वेषण 🎧 | [Clustering](5-Clustering/README.md) | K-Means क्लस्टरिंग विधि को खोजें | [Python](5-Clustering/2-K-Means/README.md) • [R](../../5-Clustering/2-K-Means/solution/R/lesson_15.html) | जेन • एरिक वांजाउ | -| 16 | प्राकृतिक भाषा संसाधन परिचय ☕️ | [Natural language processing](6-NLP/README.md) | एक सरल बोट बनाकर NLP की मूल बातें सीखें | [Python](6-NLP/1-Introduction-to-NLP/README.md) | स्टीफन | -| 17 | सामान्य NLP कार्य ☕️ | [Natural language processing](6-NLP/README.md) | भाषा संरचनाओं से निपटने के लिए आवश्यक सामान्य कार्यों को समझकर अपनी NLP ज्ञान को गहरा करें | [Python](6-NLP/2-Tasks/README.md) | स्टीफन | -| 18 | अनुवाद और भावना विश्लेषण ♥️ | [Natural language processing](6-NLP/README.md) | जेन ऑस्टेन के साथ अनुवाद और भावना विश्लेषण | [Python](6-NLP/3-Translation-Sentiment/README.md) | स्टीफन | -| 19 | यूरोप के रोमांटिक होटल ♥️ | [Natural language processing](6-NLP/README.md) | होटल समीक्षाओं के साथ भावना विश्लेषण 1 | [Python](6-NLP/4-Hotel-Reviews-1/README.md) | स्टीफन | -| 20 | यूरोप के रोमांटिक होटल ♥️ | [Natural language processing](6-NLP/README.md) | होटल समीक्षाओं के साथ भावना विश्लेषण 2 | [Python](6-NLP/5-Hotel-Reviews-2/README.md) | स्टीफन | -| 21 | टाइम सीरीज भविष्यवाणी का परिचय | [Time series](7-TimeSeries/README.md) | टाइम सीरीज भविष्यवाणी का परिचय | [Python](7-TimeSeries/1-Introduction/README.md) | फ्रांसेस्का | -| 22 | ⚡️ विश्व ऊर्जा उपयोग ⚡️ - ARIMA के साथ टाइम सीरीज भविष्यवाणी | [Time series](7-TimeSeries/README.md) | ARIMA के साथ टाइम सीरीज भविष्यवाणी | [Python](7-TimeSeries/2-ARIMA/README.md) | फ्रांसेस्का | -| 23 | ⚡️ विश्व ऊर्जा उपयोग ⚡️ - SVR के साथ टाइम सीरीज भविष्यवाणी | [Time series](7-TimeSeries/README.md) | Support Vector Regressor के साथ टाइम सीरीज भविष्यवाणी | [Python](7-TimeSeries/3-SVR/README.md) | अनिर्बान | -| 24 | सुदृढीकरण शिक्षण का परिचय | [Reinforcement learning](8-Reinforcement/README.md) | Q-Learning के साथ सुदृढीकरण शिक्षण का परिचय | [Python](8-Reinforcement/1-QLearning/README.md) | द्मित्री | -| 25 | पीटर को भेड़िये से बचाएं! 🐺 | [Reinforcement learning](8-Reinforcement/README.md) | सुदृढीकरण शिक्षण जिम | [Python](8-Reinforcement/2-Gym/README.md) | द्मित्री | -| Postscript | वास्तविक दुनिया के ML परिदृश्य और अनुप्रयोग | [ML in the Wild](9-Real-World/README.md) | क्लासिकल ML के रोचक और प्रकट करने वाले वास्तविक दुनिया अनुप्रयोग | [Lesson](9-Real-World/1-Applications/README.md) | टीम | -| Postscript | RAI डैशबोर्ड के साथ ML में मॉडल डिबगिंग | [ML in the Wild](9-Real-World/README.md) | Responsible AI डैशबोर्ड घटकों का उपयोग करके मशीन लर्निंग में मॉडल डिबगिंग | [Lesson](9-Real-World/2-Debugging-ML-Models/README.md) | रुथ याकुबू | - -> [इस पाठ्यक्रम के लिए सभी अतिरिक्त संसाधन हमारे Microsoft Learn संग्रह में खोजें](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) +- [पोस्ट-लेक्चर क्विज](https://ff-quizzes.netlify.app/en/ml/) + +> **भाषाओं के बारे में एक नोट**: ये पाठ मुख्य रूप से Python में लिखे गए हैं, लेकिन कई R में भी उपलब्ध हैं। R पाठ पूरा करने के लिए, `/solution` फ़ोल्डर पर जाएं और R पाठ खोजें। इनमें .rmd एक्सटेंशन होता है जो एक **R Markdown** फ़ाइल का प्रतिनिधित्व करता है, जिसे सरलता से `code chunks` (R या अन्य भाषाओं के) और `YAML header` (जो PDF जैसे आउटपुट को कैसे फॉर्मेट करना है, निर्देश देता है) के साथ एक `Markdown दस्तावेज़` के रूप में परिभाषित किया जा सकता है। इस प्रकार, यह डेटा साइंस के लिए एक उत्कृष्ट लेखन ढांचा प्रस्तुत करता है क्योंकि यह आपको अपने कोड, उसके आउटपुट, और अपने विचारों को Markdown में लिखने की अनुमति देता है। इसके अलावा, R Markdown दस्तावेज़ PDF, HTML, या Word जैसे आउटपुट फ़ॉर्मेट के लिए रेंडर किए जा सकते हैं। +> **क्विज़ के बारे में एक नोट**: सभी क्विज़ [Quiz App folder](../../quiz-app) में संकलित हैं, जिनमें कुल 52 क्विज़ हैं और हर एक में तीन प्रश्न हैं। ये पाठों के भीतर लिंक किए गए हैं लेकिन क्विज़ ऐप को स्थानीय रूप से भी चलाया जा सकता है; `quiz-app` फ़ोल्डर में दिए निर्देशों का पालन करें ताकि इसे स्थानीय रूप से होस्ट या Azure पर डिप्लॉय किया जा सके। + +| पाठ संख्या | विषय | पाठ समूह | सीखने के उद्देश्य | लिंक्ड पाठ | लेखक | +| :--------: | :------------------------------------------------------------: | :-----------------------------------------: | ---------------------------------------------------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------: | +| 01 | मशीन लर्निंग का परिचय | [परिचय](1-Introduction/README.md) | मशीन लर्निंग के मूलभूत सिद्धांत सीखें | [पाठ](1-Introduction/1-intro-to-ML/README.md) | मोहम्मद | +| 02 | मशीन लर्निंग का इतिहास | [परिचय](1-Introduction/README.md) | इस क्षेत्र के तहत आने वाले इतिहास को जानें | [पाठ](1-Introduction/2-history-of-ML/README.md) | जेन और एमी | +| 03 | निष्पक्षता और मशीन लर्निंग | [परिचय](1-Introduction/README.md) | मशीन लर्निंग मॉडल बनाने और लागू करने में निष्पक्षता के महत्वपूर्ण दार्शनिक मुद्दे क्या हैं जिन्हें छात्रों को ध्यान में रखना चाहिए? | [पाठ](1-Introduction/3-fairness/README.md) | टोमौमी | +| 04 | मशीन लर्निंग के तकनीकें | [परिचय](1-Introduction/README.md) | मशीन लर्निंग मॉडल बनाने के लिए शोधकर्ता किन तकनीकों का उपयोग करते हैं? | [पाठ](1-Introduction/4-techniques-of-ML/README.md) | क्रिस और जेन | +| 05 | प्रत्याशा का परिचय | [Regression](2-Regression/README.md) | प्रतिगमन मॉडल के लिए पाइथन और स्किकेट-लर्न के साथ शुरुआत करें | [Python](2-Regression/1-Tools/README.md) • [R](../../2-Regression/1-Tools/solution/R/lesson_1.html) | जेन • एरिक वांजाउ | +| 06 | उत्तर अमेरिकी कद्दू की कीमतें 🎃 | [Regression](2-Regression/README.md) | मशीन लर्निंग के लिए डेटा की सफाई और दृश्यांकन करें | [Python](2-Regression/2-Data/README.md) • [R](../../2-Regression/2-Data/solution/R/lesson_2.html) | जेन • एरिक वांजाउ | +| 07 | उत्तर अमेरिकी कद्दू की कीमतें 🎃 | [Regression](2-Regression/README.md) | रैखिक और बहुपदीय प्रतिगमन मॉडल बनाएं | [Python](2-Regression/3-Linear/README.md) • [R](../../2-Regression/3-Linear/solution/R/lesson_3.html) | जेन और दिमित्रि • एरिक वांजाउ | +| 08 | उत्तर अमेरिकी कद्दू की कीमतें 🎃 | [Regression](2-Regression/README.md) | एक लॉजिस्टिक प्रतिगमन मॉडल बनाएं | [Python](2-Regression/4-Logistic/README.md) • [R](../../2-Regression/4-Logistic/solution/R/lesson_4.html) | जेन • एरिक वांजाउ | +| 09 | एक वेब ऐप 🔌 | [Web App](3-Web-App/README.md) | अपना प्रशिक्षित मॉडल उपयोग करने के लिए एक वेब ऐप बनाएं | [Python](3-Web-App/1-Web-App/README.md) | जेन | +| 10 | वर्गीकरण का परिचय | [Classification](4-Classification/README.md) | अपने डेटा को साफ़, तैयार और विज़ुअलाइज़ करें; वर्गीकरण का परिचय | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | जेन और कैसी • एरिक वांजाउ | +| 11 | स्वादिष्ट एशियाई और भारतीय व्यंजन 🍜 | [Classification](4-Classification/README.md) | वर्गीकारकों का परिचय | [Python](4-Classification/2-Classifiers-1/README.md) • [R](../../4-Classification/2-Classifiers-1/solution/R/lesson_11.html) | जेन और कैसी • एरिक वांजाउ | +| 12 | स्वादिष्ट एशियाई और भारतीय व्यंजन 🍜 | [Classification](4-Classification/README.md) | और वर्गीकरणकर्ता | [Python](4-Classification/3-Classifiers-2/README.md) • [R](../../4-Classification/3-Classifiers-2/solution/R/lesson_12.html) | जेन और कैसी • एरिक वांजाउ | +| 13 | स्वादिष्ट एशियाई और भारतीय व्यंजन 🍜 | [Classification](4-Classification/README.md) | अपने मॉडल का उपयोग करके एक अनुशंसा वेब ऐप बनाएं | [Python](4-Classification/4-Applied/README.md) | जेन | +| 14 | क्लस्टरिंग का परिचय | [Clustering](5-Clustering/README.md) | अपने डेटा को साफ़, तैयार और विज़ुअलाइज़ करें; क्लस्टरिंग का परिचय | [Python](5-Clustering/1-Visualize/README.md) • [R](../../5-Clustering/1-Visualize/solution/R/lesson_14.html) | जेन • एरिक वांजाउ | +| 15 | नाइजीरियाई संगीत रुचियों की खोज 🎧 | [Clustering](5-Clustering/README.md) | K-मीन्स क्लस्टरिंग विधि की खोज करें | [Python](5-Clustering/2-K-Means/README.md) • [R](../../5-Clustering/2-K-Means/solution/R/lesson_15.html) | जेन • एरिक वांजाउ | +| 16 | प्राकृतिक भाषा संसाधन परिचय ☕️ | [Natural language processing](6-NLP/README.md) | एक साधारण बॉट बनाकर NLP की मूल बातें सीखें | [Python](6-NLP/1-Introduction-to-NLP/README.md) | स्टीफन | +| 17 | सामान्य NLP कार्य ☕️ | [Natural language processing](6-NLP/README.md) | भाषा संरचनाओं के साथ काम करते समय आवश्यक सामान्य कार्यों को समझकर अपना NLP ज्ञान गहरा करें | [Python](6-NLP/2-Tasks/README.md) | स्टीफन | +| 18 | अनुवाद और भाव विश्लेषण ♥️ | [Natural language processing](6-NLP/README.md) | जेन ऑस्टिन के साथ अनुवाद और भाव विश्लेषण | [Python](6-NLP/3-Translation-Sentiment/README.md) | स्टीफन | +| 19 | यूरोप के रोमांटिक होटल ♥️ | [Natural language processing](6-NLP/README.md) | होटल समीक्षाओं के साथ भावना विश्लेषण 1 | [Python](6-NLP/4-Hotel-Reviews-1/README.md) | स्टीफन | +| 20 | यूरोप के रोमांटिक होटल ♥️ | [Natural language processing](6-NLP/README.md) | होटल समीक्षाओं के साथ भावना विश्लेषण 2 | [Python](6-NLP/5-Hotel-Reviews-2/README.md) | स्टीफन | +| 21 | समय श्रृंखला पूर्वानुमान परिचय | [Time series](7-TimeSeries/README.md) | समय श्रृंखला पूर्वानुमान का परिचय | [Python](7-TimeSeries/1-Introduction/README.md) | फ्रांसेस्का | +| 22 | ⚡️ विश्व विद्युत उपयोग ⚡️ - ARIMA के साथ समय श्रृंखला पूर्वानुमान | [Time series](7-TimeSeries/README.md) | ARIMA के साथ समय श्रृंखला पूर्वानुमान | [Python](7-TimeSeries/2-ARIMA/README.md) | फ्रांसेस्का | +| 23 | ⚡️ विश्व विद्युत उपयोग ⚡️ - SVR के साथ समय श्रृंखला पूर्वानुमान | [Time series](7-TimeSeries/README.md) | सपोर्ट वेक्टर रिग्रेशन के साथ समय श्रृंखला पूर्वानुमान | [Python](7-TimeSeries/3-SVR/README.md) | अनिर्बन | +| 24 | पुनर्योजन शिक्षण का परिचय | [Reinforcement learning](8-Reinforcement/README.md) | क्यू-लर्निंग के साथ पुनर्योजन शिक्षण का परिचय | [Python](8-Reinforcement/1-QLearning/README.md) | दिमित्रि | +| 25 | पीटर को भेड़िये से बचाने में मदद करें! 🐺 | [Reinforcement learning](8-Reinforcement/README.md) | पुनर्योजन शिक्षण जिम | [Python](8-Reinforcement/2-Gym/README.md) | दिमित्रि | +| उपसंहार | वास्तविक दुनिया के ML परिदृश्य और अनुप्रयोग | [ML in the Wild](9-Real-World/README.md) | क्लासिक मशीन लर्निंग के दिलचस्प और प्रकट करने वाले वास्तविक दुनिया के अनुप्रयोग | [पाठ](9-Real-World/1-Applications/README.md) | टीम | +| उपसंहार | RAI डैशबोर्ड का उपयोग करके ML में मॉडल डिबगिंग | [ML in the Wild](9-Real-World/README.md) | जिम्मेदार AI डैशबोर्ड घटकों का उपयोग करके मशीन लर्निंग में मॉडल डिबगिंग | [पाठ](9-Real-World/2-Debugging-ML-Models/README.md) | रूथ याकूबू | + +> [इस पाठ्यक्रम के लिए हमारे Microsoft Learn संग्रह में सभी अतिरिक्त संसाधन खोजें](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) ## ऑफलाइन एक्सेस -आप इस दस्तावेज़ को ऑफलाइन [Docsify](https://docsify.js.org/#/) का उपयोग करके चला सकते हैं। इस रिपॉजिटरी को फोर्क करें, अपने स्थानीय मशीन पर [Docsify इंस्टॉल करें](https://docsify.js.org/#/quickstart), और फिर इस रिपॉजिटरी के रूट फ़ोल्डर में `docsify serve` टाइप करें। वेबसाइट आपके लोकलहोस्ट पर पोर्ट 3000 पर चलायी जाएगी: `localhost:3000`। +आप [Docsify](https://docsify.js.org/#/) का उपयोग करके इस दस्तावेज़ को ऑफलाइन चला सकते हैं। इस रिपो को फोर्क करें, अपने स्थानीय मशीन पर [Docsify इंस्टॉल करें](https://docsify.js.org/#/quickstart), और फिर इस रिपो की रूट फ़ोल्डर में `docsify serve` टाइप करें। वेबसाइट आपके लोकलहोस्ट पर पोर्ट 3000 पर सर्व की जाएगी: `localhost:3000`। ## पीडीएफ -लर्निंग पाठ्यक्रम का पीडीएफ लिंक के साथ [यहाँ](https://microsoft.github.io/ML-For-Beginners/pdf/readme.pdf) उपलब्ध है। +लिंक के साथ पाठ्यक्रम की पीडीएफ [यहाँ](https://microsoft.github.io/ML-For-Beginners/pdf/readme.pdf) पाएं। -## 🎒 अन्य पाठ्यक्रम +## 🎒 अन्य पाठ्यक्रम -हमारी टीम अन्य पाठ्यक्रम बनाती है! देखें: +हमारी टीम अन्य पाठ्यक्रम भी बनाती है! देखें: ### LangChain @@ -189,38 +169,38 @@ Microsoft के Cloud Advocates एक 12-सप्ताह, 26-पाठ क --- -### Generative AI Series -[![शुरुआत करने वालों के लिए जनरेटिव AI](https://img.shields.io/badge/Generative%20AI%20for%20Beginners-8B5CF6?style=for-the-badge&labelColor=E5E7EB&color=8B5CF6)](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst) -[![जनरेटिव AI (.NET)](https://img.shields.io/badge/Generative%20AI%20(.NET)-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst) -[![जनरेटिव AI (Java)](https://img.shields.io/badge/Generative%20AI%20(Java)-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst) -[![जनरेटिव AI (JavaScript)](https://img.shields.io/badge/Generative%20AI%20(JavaScript)-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst) +### जनरेटिव AI सीरीज +[![शुरुआत के लिए जनरेटिव एआई](https://img.shields.io/badge/Generative%20AI%20for%20Beginners-8B5CF6?style=for-the-badge&labelColor=E5E7EB&color=8B5CF6)](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst) +[![जनरेटिव एआई (.NET)](https://img.shields.io/badge/Generative%20AI%20(.NET)-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst) +[![जनरेटिव एआई (Java)](https://img.shields.io/badge/Generative%20AI%20(Java)-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst) +[![जनरेटिव एआई (JavaScript)](https://img.shields.io/badge/Generative%20AI%20(JavaScript)-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst) --- - -### मूल सीखना -[![शुरुआत करने वालों के लिए ML](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) -[![शुरुआत करने वालों के लिए डेटा साइंस](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) -[![शुरुआत करने वालों के लिए AI](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) -[![शुरुआत करने वालों के लिए साइबरसिक्योरिटी](https://img.shields.io/badge/Cybersecurity%20for%20Beginners-F97316?style=for-the-badge&labelColor=E5E7EB&color=F97316)](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung) -[![शुरुआत करने वालों के लिए वेब डेवलपमेंट](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst) -[![शुरुआत करने वालों के लिए IoT](https://img.shields.io/badge/IoT%20for%20Beginners-14B8A6?style=for-the-badge&labelColor=E5E7EB&color=14B8A6)](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst) -[![शुरुआत करने वालों के लिए XR डेवलपमेंट](https://img.shields.io/badge/XR%20Development%20for%20Beginners-38BDF8?style=for-the-badge&labelColor=E5E7EB&color=38BDF8)](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst) + +### मुख्य सीखने +[![शुरुआती के लिए एमएल](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) +[![शुरुआती के लिए डेटा साइंस](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) +[![शुरुआती के लिए एआई](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) +[![शुरुआती के लिए साइबर सुरक्षा](https://img.shields.io/badge/Cybersecurity%20for%20Beginners-F97316?style=for-the-badge&labelColor=E5E7EB&color=F97316)](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung) +[![शुरुआती के लिए वेब डेवलपमेंट](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst) +[![शुरुआती के लिए आईओटी](https://img.shields.io/badge/IoT%20for%20Beginners-14B8A6?style=for-the-badge&labelColor=E5E7EB&color=14B8A6)](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst) +[![शुरुआती के लिए एक्सआर डेवलपमेंट](https://img.shields.io/badge/XR%20Development%20for%20Beginners-38BDF8?style=for-the-badge&labelColor=E5E7EB&color=38BDF8)](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst) --- - -### कोपायलट श्रृंखला -[![AI पेयर प्रोग्रामिंग के लिए कोपायलट](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) -[![C#/.NET के लिए कोपायलट](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst) -[![कोपायलट एडवेंचर](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) + +### कोपाइलट सीरीज +[![एआई पियर्ड प्रोग्रामिंग के लिए कोपाइलट](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) +[![C#/.NET के लिए कोपाइलट](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst) +[![कोपाइलट एडवेंचर](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) -## सहायता प्राप्त करना +## मदद पाना -यदि आप फंस जाते हैं या AI ऐप बनाने के बारे में कोई सवाल है। साथी शिक्षार्थियों और अनुभवी डेवलपर्स के साथ MCP पर चर्चा में शामिल हों। यह एक सहायक समुदाय है जहाँ प्रश्न स्वागत योग्य हैं और ज्ञान स्वतंत्र रूप से साझा किया जाता है। +यदि आप अटक जाते हैं या AI ऐप्स बनाने के बारे में कोई सवाल है। MCP के बारे में चर्चा में साथ सीखने वालों और अनुभवी डेवलपर्स के साथ जुड़ें। यह एक सहायक समुदाय है जहाँ प्रश्नों का स्वागत है और ज्ञान स्वतंत्र रूप से साझा किया जाता है। [![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -यदि आपके पास उत्पाद प्रतिक्रिया या निर्माण के दौरान त्रुटियाँ हैं तो जाएँ: +यदि आपके पास उत्पाद फीडबैक है या निर्माण के दौरान त्रुटियाँ हैं, तो यहाँ जाएँ: [![Microsoft Foundry Developer Forum](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum) @@ -228,5 +208,5 @@ Microsoft के Cloud Advocates एक 12-सप्ताह, 26-पाठ क **अस्वीकरण**: -यह दस्तावेज़ AI अनुवाद सेवा [Co-op Translator](https://github.com/Azure/co-op-translator) का उपयोग करके अनुवादित किया गया है। हालांकि हम सटीकता के लिए प्रयासरत हैं, कृपया ध्यान रखें कि स्वचालित अनुवादों में त्रुटियाँ या अशुद्धियाँ हो सकती हैं। मूल दस्तावेज़ अपनी मूल भाषा में अधिकारिक स्रोत माना जाना चाहिए। महत्वपू‍र्ण जानकारी के लिए, पेशेवर मानव अनुवाद की सलाह दी जाती है। इस अनुवाद के उपयोग से उत्पन्न किसी भी गलतफहमी या गलत व्याख्या के लिए हम जिम्मेदार नहीं हैं। +यह दस्तावेज़ AI अनुवाद सेवा [Co-op Translator](https://github.com/Azure/co-op-translator) का उपयोग करके अनुवादित किया गया है। जबकि हम सटीकता के लिए प्रयासरत हैं, कृपया ध्यान दें कि स्वचालित अनुवाद में त्रुटियां या अशुद्धियां हो सकती हैं। मूल भाषा में दस्तावेज़ को अधिकारिक स्रोत माना जाना चाहिए। महत्वपूर्ण जानकारी के लिए पेशेवर मानव अनुवाद की सिफारिश की जाती है। इस अनुवाद के उपयोग से उत्पन्न किसी भी गलतफहमी या गलत व्याख्या के लिए हम जिम्मेदार नहीं हैं। \ No newline at end of file diff --git a/translations/hi/SECURITY.md b/translations/hi/SECURITY.md index 4a9e19a8f..1903e1e7c 100644 --- a/translations/hi/SECURITY.md +++ b/translations/hi/SECURITY.md @@ -1,12 +1,3 @@ - ## सुरक्षा Microsoft हमारे सॉफ़्टवेयर उत्पादों और सेवाओं की सुरक्षा को गंभीरता से लेता है, जिसमें हमारे GitHub संगठनों के माध्यम से प्रबंधित सभी स्रोत कोड रिपॉजिटरी शामिल हैं, जैसे [Microsoft](https://github.com/Microsoft), [Azure](https://github.com/Azure), [DotNet](https://github.com/dotnet), [AspNet](https://github.com/aspnet), [Xamarin](https://github.com/xamarin), और [हमारे GitHub संगठन](https://opensource.microsoft.com/)। diff --git a/translations/hi/SUPPORT.md b/translations/hi/SUPPORT.md index f3ff3836c..886c1c399 100644 --- a/translations/hi/SUPPORT.md +++ b/translations/hi/SUPPORT.md @@ -1,12 +1,3 @@ - # समर्थन ## समस्याओं को दर्ज करने और सहायता प्राप्त करने का तरीका diff --git a/translations/hi/TROUBLESHOOTING.md b/translations/hi/TROUBLESHOOTING.md index e7b44b2b2..25037ab5c 100644 --- a/translations/hi/TROUBLESHOOTING.md +++ b/translations/hi/TROUBLESHOOTING.md @@ -1,12 +1,3 @@ - # समस्या निवारण गाइड यह गाइड आपको Machine Learning for Beginners पाठ्यक्रम के साथ काम करते समय आम समस्याओं को हल करने में मदद करता है। यदि आपको यहां समाधान नहीं मिलता है, तो कृपया हमारे [Discord Discussions](https://aka.ms/foundry/discord) देखें या [एक समस्या दर्ज करें](https://github.com/microsoft/ML-For-Beginners/issues)। diff --git a/translations/hi/docs/_sidebar.md b/translations/hi/docs/_sidebar.md index 931f333d7..f18c4490b 100644 --- a/translations/hi/docs/_sidebar.md +++ b/translations/hi/docs/_sidebar.md @@ -1,12 +1,3 @@ - - परिचय - [मशीन लर्निंग का परिचय](../1-Introduction/1-intro-to-ML/README.md) - [मशीन लर्निंग का इतिहास](../1-Introduction/2-history-of-ML/README.md) diff --git a/translations/hi/for-teachers.md b/translations/hi/for-teachers.md index 644883f23..e61b8afc2 100644 --- a/translations/hi/for-teachers.md +++ b/translations/hi/for-teachers.md @@ -1,12 +1,3 @@ - ## शिक्षकों के लिए क्या आप इस पाठ्यक्रम का उपयोग अपनी कक्षा में करना चाहेंगे? कृपया बेझिझक इसका उपयोग करें! diff --git a/translations/hi/quiz-app/README.md b/translations/hi/quiz-app/README.md index f2bf644bc..d2488badf 100644 --- a/translations/hi/quiz-app/README.md +++ b/translations/hi/quiz-app/README.md @@ -1,12 +1,3 @@ - # क्विज़ ये क्विज़ ML पाठ्यक्रम के लिए पूर्व-व्याख्यान और पश्चात-व्याख्यान क्विज़ हैं, जो https://aka.ms/ml-beginners पर उपलब्ध है। diff --git a/translations/hi/sketchnotes/LICENSE.md b/translations/hi/sketchnotes/LICENSE.md index f94da1570..e91953cb5 100644 --- a/translations/hi/sketchnotes/LICENSE.md +++ b/translations/hi/sketchnotes/LICENSE.md @@ -1,12 +1,3 @@ - अट्रिब्यूशन-शेयरअलाइक 4.0 इंटरनेशनल ======================================================================= diff --git a/translations/hi/sketchnotes/README.md b/translations/hi/sketchnotes/README.md index 2f82887cb..638641b72 100644 --- a/translations/hi/sketchnotes/README.md +++ b/translations/hi/sketchnotes/README.md @@ -1,12 +1,3 @@ - सभी पाठ्यक्रम के स्केच नोट्स यहां से डाउनलोड किए जा सकते हैं। 🖨 उच्च-रिज़ॉल्यूशन में प्रिंटिंग के लिए, TIFF संस्करण [इस रिपॉजिटरी](https://github.com/girliemac/a-picture-is-worth-a-1000-words/tree/main/ml/tiff) में उपलब्ध हैं। diff --git a/translations/ja/.co-op-translator.json b/translations/ja/.co-op-translator.json new file mode 100644 index 000000000..b86f33126 --- /dev/null +++ b/translations/ja/.co-op-translator.json @@ -0,0 +1,596 @@ +{ + "1-Introduction/1-intro-to-ML/README.md": { + "original_hash": "69389392fa6346e0dfa30f664b7b6fec", + "translation_date": "2025-09-06T09:34:38+00:00", + "source_file": "1-Introduction/1-intro-to-ML/README.md", + "language_code": "ja" + }, + "1-Introduction/1-intro-to-ML/assignment.md": { + "original_hash": "4c4698044bb8af52cfb6388a4ee0e53b", + "translation_date": "2025-09-03T23:38:30+00:00", + "source_file": "1-Introduction/1-intro-to-ML/assignment.md", + "language_code": "ja" + }, + "1-Introduction/2-history-of-ML/README.md": { + "original_hash": "6a05fec147e734c3e6bfa54505648e2b", + "translation_date": "2025-09-06T09:35:08+00:00", + "source_file": "1-Introduction/2-history-of-ML/README.md", + "language_code": "ja" + }, + "1-Introduction/2-history-of-ML/assignment.md": { + "original_hash": "eb6e4d5afd1b21a57d2b9e6d0aac3969", + "translation_date": "2025-09-03T23:42:26+00:00", + "source_file": "1-Introduction/2-history-of-ML/assignment.md", + "language_code": "ja" + }, + "1-Introduction/3-fairness/README.md": { + "original_hash": "9a6b702d1437c0467e3c5c28d763dac2", + "translation_date": "2025-09-06T09:33:20+00:00", + "source_file": "1-Introduction/3-fairness/README.md", + "language_code": "ja" + }, + "1-Introduction/3-fairness/assignment.md": { + "original_hash": "dbda60e7b1fe5f18974e7858eff0004e", + "translation_date": "2025-09-03T23:31:14+00:00", + "source_file": "1-Introduction/3-fairness/assignment.md", + "language_code": "ja" + }, + "1-Introduction/4-techniques-of-ML/README.md": { + "original_hash": "9d91f3af3758fdd4569fb410575995ef", + "translation_date": "2025-09-06T09:34:02+00:00", + "source_file": "1-Introduction/4-techniques-of-ML/README.md", + "language_code": "ja" + }, + "1-Introduction/4-techniques-of-ML/assignment.md": { + "original_hash": "70d65aeddc06170bc1aed5b27805f930", + "translation_date": "2025-09-03T23:35:11+00:00", + "source_file": "1-Introduction/4-techniques-of-ML/assignment.md", + "language_code": "ja" + }, + "1-Introduction/README.md": { + "original_hash": "cf8ecc83f28e5b98051d2179eca08e08", + "translation_date": "2025-09-03T23:25:54+00:00", + "source_file": "1-Introduction/README.md", + "language_code": "ja" + }, + "2-Regression/1-Tools/README.md": { + "original_hash": "fa81d226c71d5af7a2cade31c1c92b88", + "translation_date": "2025-09-06T09:27:16+00:00", + "source_file": "2-Regression/1-Tools/README.md", + "language_code": "ja" + }, + "2-Regression/1-Tools/assignment.md": { + "original_hash": "74a5cf83e4ebc302afbcbc4f418afd0a", + "translation_date": "2025-09-03T22:36:13+00:00", + "source_file": "2-Regression/1-Tools/assignment.md", + "language_code": "ja" + }, + "2-Regression/1-Tools/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T22:36:46+00:00", + "source_file": "2-Regression/1-Tools/solution/Julia/README.md", + "language_code": "ja" + }, + "2-Regression/2-Data/README.md": { + "original_hash": "7c077988328ebfe33b24d07945f16eca", + "translation_date": "2025-09-06T09:27:59+00:00", + "source_file": "2-Regression/2-Data/README.md", + "language_code": "ja" + }, + "2-Regression/2-Data/assignment.md": { + "original_hash": "4485a1ed4dd1b5647365e3d87456515d", + "translation_date": "2025-09-03T22:40:20+00:00", + "source_file": "2-Regression/2-Data/assignment.md", + "language_code": "ja" + }, + "2-Regression/2-Data/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T22:40:48+00:00", + "source_file": "2-Regression/2-Data/solution/Julia/README.md", + "language_code": "ja" + }, + "2-Regression/3-Linear/README.md": { + "original_hash": "40e64f004f3cb50aa1d8661672d3cd92", + "translation_date": "2025-09-06T09:24:27+00:00", + "source_file": "2-Regression/3-Linear/README.md", + "language_code": "ja" + }, + "2-Regression/3-Linear/assignment.md": { + "original_hash": "cc471fa89c293bc735dd3a9a0fb79b1b", + "translation_date": "2025-09-03T22:22:04+00:00", + "source_file": "2-Regression/3-Linear/assignment.md", + "language_code": "ja" + }, + "2-Regression/3-Linear/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T22:22:34+00:00", + "source_file": "2-Regression/3-Linear/solution/Julia/README.md", + "language_code": "ja" + }, + "2-Regression/4-Logistic/README.md": { + "original_hash": "abf86d845c84330bce205a46b382ec88", + "translation_date": "2025-09-06T09:26:24+00:00", + "source_file": "2-Regression/4-Logistic/README.md", + "language_code": "ja" + }, + "2-Regression/4-Logistic/assignment.md": { + "original_hash": "8af40209a41494068c1f42b14c0b450d", + "translation_date": "2025-09-03T22:31:11+00:00", + "source_file": "2-Regression/4-Logistic/assignment.md", + "language_code": "ja" + }, + "2-Regression/4-Logistic/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T22:31:40+00:00", + "source_file": "2-Regression/4-Logistic/solution/Julia/README.md", + "language_code": "ja" + }, + "2-Regression/README.md": { + "original_hash": "508582278dbb8edd2a8a80ac96ef416c", + "translation_date": "2025-09-03T22:15:04+00:00", + "source_file": "2-Regression/README.md", + "language_code": "ja" + }, + "3-Web-App/1-Web-App/README.md": { + "original_hash": "e0b75f73e4a90d45181dc5581fe2ef5c", + "translation_date": "2025-09-06T09:35:43+00:00", + "source_file": "3-Web-App/1-Web-App/README.md", + "language_code": "ja" + }, + "3-Web-App/1-Web-App/assignment.md": { + "original_hash": "a8e8ae10be335cbc745b75ee552317ff", + "translation_date": "2025-09-03T23:47:10+00:00", + "source_file": "3-Web-App/1-Web-App/assignment.md", + "language_code": "ja" + }, + "3-Web-App/README.md": { + "original_hash": "9836ff53cfef716ddfd70e06c5f43436", + "translation_date": "2025-09-03T23:43:01+00:00", + "source_file": "3-Web-App/README.md", + "language_code": "ja" + }, + "4-Classification/1-Introduction/README.md": { + "original_hash": "aaf391d922bd6de5efba871d514c6d47", + "translation_date": "2025-09-06T09:37:48+00:00", + "source_file": "4-Classification/1-Introduction/README.md", + "language_code": "ja" + }, + "4-Classification/1-Introduction/assignment.md": { + "original_hash": "b2a01912beb24cfb0007f83594dba801", + "translation_date": "2025-09-04T00:03:59+00:00", + "source_file": "4-Classification/1-Introduction/assignment.md", + "language_code": "ja" + }, + "4-Classification/1-Introduction/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-04T00:04:33+00:00", + "source_file": "4-Classification/1-Introduction/solution/Julia/README.md", + "language_code": "ja" + }, + "4-Classification/2-Classifiers-1/README.md": { + "original_hash": "1a6e9e46b34a2e559fbbfc1f95397c7b", + "translation_date": "2025-09-06T09:36:18+00:00", + "source_file": "4-Classification/2-Classifiers-1/README.md", + "language_code": "ja" + }, + "4-Classification/2-Classifiers-1/assignment.md": { + "original_hash": "de6025f96841498b0577e9d1aee18d1f", + "translation_date": "2025-09-03T23:53:57+00:00", + "source_file": "4-Classification/2-Classifiers-1/assignment.md", + "language_code": "ja" + }, + "4-Classification/2-Classifiers-1/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T23:54:30+00:00", + "source_file": "4-Classification/2-Classifiers-1/solution/Julia/README.md", + "language_code": "ja" + }, + "4-Classification/3-Classifiers-2/README.md": { + "original_hash": "49047911108adc49d605cddfb455749c", + "translation_date": "2025-09-06T09:37:28+00:00", + "source_file": "4-Classification/3-Classifiers-2/README.md", + "language_code": "ja" + }, + "4-Classification/3-Classifiers-2/assignment.md": { + "original_hash": "58dfdaf79fb73f7d34b22bdbacf57329", + "translation_date": "2025-09-03T23:59:57+00:00", + "source_file": "4-Classification/3-Classifiers-2/assignment.md", + "language_code": "ja" + }, + "4-Classification/3-Classifiers-2/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-04T00:00:47+00:00", + "source_file": "4-Classification/3-Classifiers-2/solution/Julia/README.md", + "language_code": "ja" + }, + "4-Classification/4-Applied/README.md": { + "original_hash": "61bdec27ed2da8b098cd9065405d9bb0", + "translation_date": "2025-09-06T09:37:03+00:00", + "source_file": "4-Classification/4-Applied/README.md", + "language_code": "ja" + }, + "4-Classification/4-Applied/assignment.md": { + "original_hash": "799ed651e2af0a7cad17c6268db11578", + "translation_date": "2025-09-03T23:57:21+00:00", + "source_file": "4-Classification/4-Applied/assignment.md", + "language_code": "ja" + }, + "4-Classification/README.md": { + "original_hash": "74e809ffd1e613a1058bbc3e9600859e", + "translation_date": "2025-09-03T23:48:56+00:00", + "source_file": "4-Classification/README.md", + "language_code": "ja" + }, + "5-Clustering/1-Visualize/README.md": { + "original_hash": "730225ea274c9174fe688b21d421539d", + "translation_date": "2025-09-06T09:30:23+00:00", + "source_file": "5-Clustering/1-Visualize/README.md", + "language_code": "ja" + }, + "5-Clustering/1-Visualize/assignment.md": { + "original_hash": "589fa015a5e7d9e67bd629f7d47b53de", + "translation_date": "2025-09-03T23:09:07+00:00", + "source_file": "5-Clustering/1-Visualize/assignment.md", + "language_code": "ja" + }, + "5-Clustering/1-Visualize/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T23:09:43+00:00", + "source_file": "5-Clustering/1-Visualize/solution/Julia/README.md", + "language_code": "ja" + }, + "5-Clustering/2-K-Means/README.md": { + "original_hash": "7cdd17338d9bbd7e2171c2cd462eb081", + "translation_date": "2025-09-06T09:31:24+00:00", + "source_file": "5-Clustering/2-K-Means/README.md", + "language_code": "ja" + }, + "5-Clustering/2-K-Means/assignment.md": { + "original_hash": "b8e17eff34ad1680eba2a5d3cf9ffc41", + "translation_date": "2025-09-03T23:12:44+00:00", + "source_file": "5-Clustering/2-K-Means/assignment.md", + "language_code": "ja" + }, + "5-Clustering/2-K-Means/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T23:13:15+00:00", + "source_file": "5-Clustering/2-K-Means/solution/Julia/README.md", + "language_code": "ja" + }, + "5-Clustering/README.md": { + "original_hash": "b28a3a4911584062772c537b653ebbc7", + "translation_date": "2025-09-03T22:55:43+00:00", + "source_file": "5-Clustering/README.md", + "language_code": "ja" + }, + "6-NLP/1-Introduction-to-NLP/README.md": { + "original_hash": "1c2ec40cf55c98a028a359c27ef7e45a", + "translation_date": "2025-09-06T09:42:06+00:00", + "source_file": "6-NLP/1-Introduction-to-NLP/README.md", + "language_code": "ja" + }, + "6-NLP/1-Introduction-to-NLP/assignment.md": { + "original_hash": "1d7583e8046dacbb0c056d5ba0a71b16", + "translation_date": "2025-09-04T00:49:04+00:00", + "source_file": "6-NLP/1-Introduction-to-NLP/assignment.md", + "language_code": "ja" + }, + "6-NLP/2-Tasks/README.md": { + "original_hash": "5f3cb462e3122e1afe7ab0050ccf2bd3", + "translation_date": "2025-09-06T09:40:24+00:00", + "source_file": "6-NLP/2-Tasks/README.md", + "language_code": "ja" + }, + "6-NLP/2-Tasks/assignment.md": { + "original_hash": "2efc4c2aba5ed06c780c05539c492ae3", + "translation_date": "2025-09-04T00:37:13+00:00", + "source_file": "6-NLP/2-Tasks/assignment.md", + "language_code": "ja" + }, + "6-NLP/3-Translation-Sentiment/README.md": { + "original_hash": "be03c8182982b87ced155e4e9d1438e8", + "translation_date": "2025-09-06T09:42:39+00:00", + "source_file": "6-NLP/3-Translation-Sentiment/README.md", + "language_code": "ja" + }, + "6-NLP/3-Translation-Sentiment/assignment.md": { + "original_hash": "9d2a734deb904caff310d1a999c6bd7a", + "translation_date": "2025-09-04T00:53:50+00:00", + "source_file": "6-NLP/3-Translation-Sentiment/assignment.md", + "language_code": "ja" + }, + "6-NLP/3-Translation-Sentiment/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-04T00:54:43+00:00", + "source_file": "6-NLP/3-Translation-Sentiment/solution/Julia/README.md", + "language_code": "ja" + }, + "6-NLP/3-Translation-Sentiment/solution/R/README.md": { + "original_hash": "81db6ff2cf6e62fbe2340b094bb9509e", + "translation_date": "2025-09-04T00:54:24+00:00", + "source_file": "6-NLP/3-Translation-Sentiment/solution/R/README.md", + "language_code": "ja" + }, + "6-NLP/4-Hotel-Reviews-1/README.md": { + "original_hash": "8d32dadeda93c6fb5c43619854882ab1", + "translation_date": "2025-09-06T09:40:57+00:00", + "source_file": "6-NLP/4-Hotel-Reviews-1/README.md", + "language_code": "ja" + }, + "6-NLP/4-Hotel-Reviews-1/assignment.md": { + "original_hash": "bf39bceb833cd628f224941dca8041df", + "translation_date": "2025-09-04T00:44:23+00:00", + "source_file": "6-NLP/4-Hotel-Reviews-1/assignment.md", + "language_code": "ja" + }, + "6-NLP/4-Hotel-Reviews-1/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-04T00:45:08+00:00", + "source_file": "6-NLP/4-Hotel-Reviews-1/solution/Julia/README.md", + "language_code": "ja" + }, + "6-NLP/4-Hotel-Reviews-1/solution/R/README.md": { + "original_hash": "81db6ff2cf6e62fbe2340b094bb9509e", + "translation_date": "2025-09-04T00:44:50+00:00", + "source_file": "6-NLP/4-Hotel-Reviews-1/solution/R/README.md", + "language_code": "ja" + }, + "6-NLP/5-Hotel-Reviews-2/README.md": { + "original_hash": "2c742993fe95d5bcbb2846eda3d442a1", + "translation_date": "2025-09-06T09:43:24+00:00", + "source_file": "6-NLP/5-Hotel-Reviews-2/README.md", + "language_code": "ja" + }, + "6-NLP/5-Hotel-Reviews-2/assignment.md": { + "original_hash": "daf144daa552da6a7d442aff6f3e77d8", + "translation_date": "2025-09-04T00:59:44+00:00", + "source_file": "6-NLP/5-Hotel-Reviews-2/assignment.md", + "language_code": "ja" + }, + "6-NLP/5-Hotel-Reviews-2/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-04T01:00:33+00:00", + "source_file": "6-NLP/5-Hotel-Reviews-2/solution/Julia/README.md", + "language_code": "ja" + }, + "6-NLP/5-Hotel-Reviews-2/solution/R/README.md": { + "original_hash": "81db6ff2cf6e62fbe2340b094bb9509e", + "translation_date": "2025-09-04T01:00:13+00:00", + "source_file": "6-NLP/5-Hotel-Reviews-2/solution/R/README.md", + "language_code": "ja" + }, + "6-NLP/README.md": { + "original_hash": "1eb379dc2d0c9940b320732d16083778", + "translation_date": "2025-09-04T00:33:00+00:00", + "source_file": "6-NLP/README.md", + "language_code": "ja" + }, + "6-NLP/data/README.md": { + "original_hash": "ee0670655c89e4719319764afb113624", + "translation_date": "2025-09-04T00:45:28+00:00", + "source_file": "6-NLP/data/README.md", + "language_code": "ja" + }, + "7-TimeSeries/1-Introduction/README.md": { + "original_hash": "662b509c39eee205687726636d0a8455", + "translation_date": "2025-09-06T09:29:16+00:00", + "source_file": "7-TimeSeries/1-Introduction/README.md", + "language_code": "ja" + }, + "7-TimeSeries/1-Introduction/assignment.md": { + "original_hash": "d1781b0b92568ea1d119d0a198b576b4", + "translation_date": "2025-09-03T22:50:45+00:00", + "source_file": "7-TimeSeries/1-Introduction/assignment.md", + "language_code": "ja" + }, + "7-TimeSeries/1-Introduction/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T22:51:38+00:00", + "source_file": "7-TimeSeries/1-Introduction/solution/Julia/README.md", + "language_code": "ja" + }, + "7-TimeSeries/1-Introduction/solution/R/README.md": { + "original_hash": "81db6ff2cf6e62fbe2340b094bb9509e", + "translation_date": "2025-09-03T22:51:18+00:00", + "source_file": "7-TimeSeries/1-Introduction/solution/R/README.md", + "language_code": "ja" + }, + "7-TimeSeries/2-ARIMA/README.md": { + "original_hash": "917dbf890db71a322f306050cb284749", + "translation_date": "2025-09-06T09:28:34+00:00", + "source_file": "7-TimeSeries/2-ARIMA/README.md", + "language_code": "ja" + }, + "7-TimeSeries/2-ARIMA/assignment.md": { + "original_hash": "1c814013e10866dfd92cdb32caaae3ac", + "translation_date": "2025-09-03T22:46:20+00:00", + "source_file": "7-TimeSeries/2-ARIMA/assignment.md", + "language_code": "ja" + }, + "7-TimeSeries/2-ARIMA/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T22:47:08+00:00", + "source_file": "7-TimeSeries/2-ARIMA/solution/Julia/README.md", + "language_code": "ja" + }, + "7-TimeSeries/2-ARIMA/solution/R/README.md": { + "original_hash": "81db6ff2cf6e62fbe2340b094bb9509e", + "translation_date": "2025-09-03T22:46:49+00:00", + "source_file": "7-TimeSeries/2-ARIMA/solution/R/README.md", + "language_code": "ja" + }, + "7-TimeSeries/3-SVR/README.md": { + "original_hash": "482bccabe1df958496ea71a3667995cd", + "translation_date": "2025-09-06T09:29:52+00:00", + "source_file": "7-TimeSeries/3-SVR/README.md", + "language_code": "ja" + }, + "7-TimeSeries/3-SVR/assignment.md": { + "original_hash": "94aa2fc6154252ae30a3f3740299707a", + "translation_date": "2025-09-03T22:54:57+00:00", + "source_file": "7-TimeSeries/3-SVR/assignment.md", + "language_code": "ja" + }, + "7-TimeSeries/README.md": { + "original_hash": "61342603bad8acadbc6b2e4e3aab3f66", + "translation_date": "2025-09-03T22:41:12+00:00", + "source_file": "7-TimeSeries/README.md", + "language_code": "ja" + }, + "8-Reinforcement/1-QLearning/README.md": { + "original_hash": "911efd5e595089000cb3c16fce1beab8", + "translation_date": "2025-09-06T09:39:02+00:00", + "source_file": "8-Reinforcement/1-QLearning/README.md", + "language_code": "ja" + }, + "8-Reinforcement/1-QLearning/assignment.md": { + "original_hash": "68394b2102d3503882e5e914bd0ff5c1", + "translation_date": "2025-09-04T00:23:31+00:00", + "source_file": "8-Reinforcement/1-QLearning/assignment.md", + "language_code": "ja" + }, + "8-Reinforcement/1-QLearning/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-04T00:25:31+00:00", + "source_file": "8-Reinforcement/1-QLearning/solution/Julia/README.md", + "language_code": "ja" + }, + "8-Reinforcement/1-QLearning/solution/R/README.md": { + "original_hash": "81db6ff2cf6e62fbe2340b094bb9509e", + "translation_date": "2025-09-04T00:25:13+00:00", + "source_file": "8-Reinforcement/1-QLearning/solution/R/README.md", + "language_code": "ja" + }, + "8-Reinforcement/2-Gym/README.md": { + "original_hash": "107d5bb29da8a562e7ae72262d251a75", + "translation_date": "2025-09-06T09:39:42+00:00", + "source_file": "8-Reinforcement/2-Gym/README.md", + "language_code": "ja" + }, + "8-Reinforcement/2-Gym/assignment.md": { + "original_hash": "1f2b7441745eb52e25745423b247016b", + "translation_date": "2025-09-04T00:31:08+00:00", + "source_file": "8-Reinforcement/2-Gym/assignment.md", + "language_code": "ja" + }, + "8-Reinforcement/2-Gym/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-04T00:32:36+00:00", + "source_file": "8-Reinforcement/2-Gym/solution/Julia/README.md", + "language_code": "ja" + }, + "8-Reinforcement/2-Gym/solution/R/README.md": { + "original_hash": "81db6ff2cf6e62fbe2340b094bb9509e", + "translation_date": "2025-09-04T00:32:17+00:00", + "source_file": "8-Reinforcement/2-Gym/solution/R/README.md", + "language_code": "ja" + }, + "8-Reinforcement/README.md": { + "original_hash": "20ca019012b1725de956681d036d8b18", + "translation_date": "2025-09-04T00:13:47+00:00", + "source_file": "8-Reinforcement/README.md", + "language_code": "ja" + }, + "9-Real-World/1-Applications/README.md": { + "original_hash": "83320d6b6994909e35d830cebf214039", + "translation_date": "2025-09-06T09:31:49+00:00", + "source_file": "9-Real-World/1-Applications/README.md", + "language_code": "ja" + }, + "9-Real-World/1-Applications/assignment.md": { + "original_hash": "fdebfcd0a3f12c9e2b436ded1aa79885", + "translation_date": "2025-09-03T23:19:26+00:00", + "source_file": "9-Real-World/1-Applications/assignment.md", + "language_code": "ja" + }, + "9-Real-World/2-Debugging-ML-Models/README.md": { + "original_hash": "df2b538e8fbb3e91cf0419ae2f858675", + "translation_date": "2025-09-06T09:32:28+00:00", + "source_file": "9-Real-World/2-Debugging-ML-Models/README.md", + "language_code": "ja" + }, + "9-Real-World/2-Debugging-ML-Models/assignment.md": { + "original_hash": "91c6a180ef08e20cc15acfd2d6d6e164", + "translation_date": "2025-09-03T23:25:15+00:00", + "source_file": "9-Real-World/2-Debugging-ML-Models/assignment.md", + "language_code": "ja" + }, + "9-Real-World/README.md": { + "original_hash": "5e069a0ac02a9606a69946c2b3c574a9", + "translation_date": "2025-09-03T23:14:34+00:00", + "source_file": "9-Real-World/README.md", + "language_code": "ja" + }, + "AGENTS.md": { + "original_hash": "93fdaa0fd38836e50c4793e2f2f25e8b", + "translation_date": "2025-10-03T11:01:56+00:00", + "source_file": "AGENTS.md", + "language_code": "ja" + }, + "CODE_OF_CONDUCT.md": { + "original_hash": "c06b12caf3c901eb3156e3dd5b0aea56", + "translation_date": "2025-09-03T22:14:28+00:00", + "source_file": "CODE_OF_CONDUCT.md", + "language_code": "ja" + }, + "CONTRIBUTING.md": { + "original_hash": "977ec5266dfd78ad1ce2bd8d46fccbda", + "translation_date": "2025-09-03T22:11:43+00:00", + "source_file": "CONTRIBUTING.md", + "language_code": "ja" + }, + "README.md": { + "original_hash": "da2ceed62f16a0820259556e3a873c95", + "translation_date": "2026-01-29T18:02:42+00:00", + "source_file": "README.md", + "language_code": "ja" + }, + "SECURITY.md": { + "original_hash": "5e1b8da31aae9cca3d53ad243fa3365a", + "translation_date": "2025-09-03T22:12:30+00:00", + "source_file": "SECURITY.md", + "language_code": "ja" + }, + "SUPPORT.md": { + "original_hash": "09623d7343ff1c26ff4f198c1b2d3176", + "translation_date": "2025-10-03T11:46:56+00:00", + "source_file": "SUPPORT.md", + "language_code": "ja" + }, + "TROUBLESHOOTING.md": { + "original_hash": "134d8759f0e2ab886e9aa4f62362c201", + "translation_date": "2025-10-03T12:40:05+00:00", + "source_file": "TROUBLESHOOTING.md", + "language_code": "ja" + }, + "docs/_sidebar.md": { + "original_hash": "68dd06c685f6ce840e0acfa313352e7c", + "translation_date": "2025-09-03T23:13:39+00:00", + "source_file": "docs/_sidebar.md", + "language_code": "ja" + }, + "for-teachers.md": { + "original_hash": "b37de02054fa6c0438ede6fabe1fdfb8", + "translation_date": "2025-09-03T22:13:38+00:00", + "source_file": "for-teachers.md", + "language_code": "ja" + }, + "quiz-app/README.md": { + "original_hash": "6d130dffca5db70d7e615f926cb1ad4c", + "translation_date": "2025-09-03T23:47:49+00:00", + "source_file": "quiz-app/README.md", + "language_code": "ja" + }, + "sketchnotes/LICENSE.md": { + "original_hash": "fba3b94d88bfb9b81369b869a1e9a20f", + "translation_date": "2025-09-04T00:07:30+00:00", + "source_file": "sketchnotes/LICENSE.md", + "language_code": "ja" + }, + "sketchnotes/README.md": { + "original_hash": "a88d5918c1b9da69a40d917a0840c497", + "translation_date": "2025-09-04T00:04:53+00:00", + "source_file": "sketchnotes/README.md", + "language_code": "ja" + } +} \ No newline at end of file diff --git a/translations/ja/1-Introduction/1-intro-to-ML/README.md b/translations/ja/1-Introduction/1-intro-to-ML/README.md index 857bd7e2c..ca20a15c2 100644 --- a/translations/ja/1-Introduction/1-intro-to-ML/README.md +++ b/translations/ja/1-Introduction/1-intro-to-ML/README.md @@ -1,12 +1,3 @@ - # 機械学習の入門 ## [講義前のクイズ](https://ff-quizzes.netlify.app/en/ml/) diff --git a/translations/ja/1-Introduction/1-intro-to-ML/assignment.md b/translations/ja/1-Introduction/1-intro-to-ML/assignment.md index fc6f0e794..5c1ddca07 100644 --- a/translations/ja/1-Introduction/1-intro-to-ML/assignment.md +++ b/translations/ja/1-Introduction/1-intro-to-ML/assignment.md @@ -1,12 +1,3 @@ - # 起動と準備 ## 手順 diff --git a/translations/ja/1-Introduction/2-history-of-ML/README.md b/translations/ja/1-Introduction/2-history-of-ML/README.md index bb0a17a78..9caac3797 100644 --- a/translations/ja/1-Introduction/2-history-of-ML/README.md +++ b/translations/ja/1-Introduction/2-history-of-ML/README.md @@ -1,12 +1,3 @@ - # 機械学習の歴史 ![機械学習の歴史の概要をスケッチノートで表現](../../../../sketchnotes/ml-history.png) diff --git a/translations/ja/1-Introduction/2-history-of-ML/assignment.md b/translations/ja/1-Introduction/2-history-of-ML/assignment.md index 24f558d21..d372ecca1 100644 --- a/translations/ja/1-Introduction/2-history-of-ML/assignment.md +++ b/translations/ja/1-Introduction/2-history-of-ML/assignment.md @@ -1,12 +1,3 @@ - # タイムラインを作成する ## 手順 diff --git a/translations/ja/1-Introduction/3-fairness/README.md b/translations/ja/1-Introduction/3-fairness/README.md index f1e06debb..87b7db14b 100644 --- a/translations/ja/1-Introduction/3-fairness/README.md +++ b/translations/ja/1-Introduction/3-fairness/README.md @@ -1,12 +1,3 @@ - # 責任あるAIを用いた機械学習ソリューションの構築 ![機械学習における責任あるAIの概要を示すスケッチノート](../../../../sketchnotes/ml-fairness.png) diff --git a/translations/ja/1-Introduction/3-fairness/assignment.md b/translations/ja/1-Introduction/3-fairness/assignment.md index 617b24914..1edd5e1ce 100644 --- a/translations/ja/1-Introduction/3-fairness/assignment.md +++ b/translations/ja/1-Introduction/3-fairness/assignment.md @@ -1,12 +1,3 @@ - # 責任あるAIツールボックスを探る ## 手順 diff --git a/translations/ja/1-Introduction/4-techniques-of-ML/README.md b/translations/ja/1-Introduction/4-techniques-of-ML/README.md index 3ab73e78f..0cb46e2f6 100644 --- a/translations/ja/1-Introduction/4-techniques-of-ML/README.md +++ b/translations/ja/1-Introduction/4-techniques-of-ML/README.md @@ -1,12 +1,3 @@ - # 機械学習の技術 機械学習モデルとその使用データを構築、利用、維持するプロセスは、他の多くの開発ワークフローとは大きく異なります。このレッスンでは、そのプロセスを解明し、知っておくべき主要な技術を概説します。以下を学びます： diff --git a/translations/ja/1-Introduction/4-techniques-of-ML/assignment.md b/translations/ja/1-Introduction/4-techniques-of-ML/assignment.md index caa8179ac..f2f192451 100644 --- a/translations/ja/1-Introduction/4-techniques-of-ML/assignment.md +++ b/translations/ja/1-Introduction/4-techniques-of-ML/assignment.md @@ -1,12 +1,3 @@ - # データサイエンティストへのインタビュー ## 指示 diff --git a/translations/ja/1-Introduction/README.md b/translations/ja/1-Introduction/README.md index 3eb48f5b4..927ef0e56 100644 --- a/translations/ja/1-Introduction/README.md +++ b/translations/ja/1-Introduction/README.md @@ -1,12 +1,3 @@ - # 機械学習の入門 このカリキュラムのセクションでは、機械学習の分野の基本的な概念、それが何であるか、その歴史、そして研究者がそれに取り組むために使用する技術について学びます。一緒にこの新しい機械学習の世界を探求してみましょう！ diff --git a/translations/ja/2-Regression/1-Tools/README.md b/translations/ja/2-Regression/1-Tools/README.md index 2b3b77a7d..74a61cf4a 100644 --- a/translations/ja/2-Regression/1-Tools/README.md +++ b/translations/ja/2-Regression/1-Tools/README.md @@ -1,12 +1,3 @@ - # PythonとScikit-learnを使った回帰モデルの入門 ![回帰の概要をスケッチノートで表現](../../../../sketchnotes/ml-regression.png) diff --git a/translations/ja/2-Regression/1-Tools/assignment.md b/translations/ja/2-Regression/1-Tools/assignment.md index f180cfee2..b21ebba18 100644 --- a/translations/ja/2-Regression/1-Tools/assignment.md +++ b/translations/ja/2-Regression/1-Tools/assignment.md @@ -1,12 +1,3 @@ - # Scikit-learnによる回帰分析 ## 手順 diff --git a/translations/ja/2-Regression/1-Tools/solution/Julia/README.md b/translations/ja/2-Regression/1-Tools/solution/Julia/README.md index 66e3035c3..6c5b00136 100644 --- a/translations/ja/2-Regression/1-Tools/solution/Julia/README.md +++ b/translations/ja/2-Regression/1-Tools/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ja/2-Regression/2-Data/README.md b/translations/ja/2-Regression/2-Data/README.md index 26afdfdfa..aa3fe1ea8 100644 --- a/translations/ja/2-Regression/2-Data/README.md +++ b/translations/ja/2-Regression/2-Data/README.md @@ -1,12 +1,3 @@ - # Scikit-learnを使った回帰モデルの構築：データの準備と可視化 ![データ可視化のインフォグラフィック](../../../../2-Regression/2-Data/images/data-visualization.png) diff --git a/translations/ja/2-Regression/2-Data/assignment.md b/translations/ja/2-Regression/2-Data/assignment.md index 8eaa57660..9ee8a0fc3 100644 --- a/translations/ja/2-Regression/2-Data/assignment.md +++ b/translations/ja/2-Regression/2-Data/assignment.md @@ -1,12 +1,3 @@ - # 可視化の探求 データ可視化に利用できるさまざまなライブラリがあります。このレッスンで使用するカボチャデータを使って、matplotlibとseabornを使用してサンプルノートブックでいくつかの可視化を作成してください。どのライブラリが使いやすいですか？ diff --git a/translations/ja/2-Regression/2-Data/solution/Julia/README.md b/translations/ja/2-Regression/2-Data/solution/Julia/README.md index 04653716e..6c5b00136 100644 --- a/translations/ja/2-Regression/2-Data/solution/Julia/README.md +++ b/translations/ja/2-Regression/2-Data/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ja/2-Regression/3-Linear/README.md b/translations/ja/2-Regression/3-Linear/README.md index e4694cbe0..cf19cb04b 100644 --- a/translations/ja/2-Regression/3-Linear/README.md +++ b/translations/ja/2-Regression/3-Linear/README.md @@ -1,12 +1,3 @@ - # Scikit-learnを使った回帰モデルの構築：4つの方法で回帰を学ぶ ![線形回帰と多項式回帰のインフォグラフィック](../../../../2-Regression/3-Linear/images/linear-polynomial.png) @@ -113,11 +104,11 @@ day_of_year = pd.to_datetime(pumpkins['Date']).apply(lambda dt: (dt-datetime(dt. 前回のレッスンで、月ごとの平均価格が次のように見えることを確認しました： -月ごとの平均価格 +月ごとの平均価格 これは、何らかの相関があることを示唆しており、`Month`と`Price`、または`DayOfYear`と`Price`の関係を予測する線形回帰モデルをトレーニングすることを試みる価値があります。以下は、後者の関係を示す散布図です： -価格と年の日数の散布図 +価格と年の日数の散布図 `corr`関数を使用して相関を確認してみましょう： @@ -136,7 +127,7 @@ for i,var in enumerate(new_pumpkins['Variety'].unique()): ax = df.plot.scatter('DayOfYear','Price',ax=ax,c=colors[i],label=var) ``` -価格と年の日数の散布図（色分け） +価格と年の日数の散布図（色分け） 調査の結果、販売日よりも品種が価格全体に与える影響が大きいことが示唆されます。これを棒グラフで確認できます： @@ -144,7 +135,7 @@ for i,var in enumerate(new_pumpkins['Variety'].unique()): new_pumpkins.groupby('Variety')['Price'].mean().plot(kind='bar') ``` -品種ごとの価格の棒グラフ +品種ごとの価格の棒グラフ ここでは、特定のカボチャ品種「パイタイプ」に焦点を当て、日付が価格に与える影響を見てみましょう： @@ -152,7 +143,7 @@ new_pumpkins.groupby('Variety')['Price'].mean().plot(kind='bar') pie_pumpkins = new_pumpkins[new_pumpkins['Variety']=='PIE TYPE'] pie_pumpkins.plot.scatter('DayOfYear','Price') ``` -価格と年の日数の散布図（パイタイプ） +価格と年の日数の散布図（パイタイプ） `corr`関数を使用して`Price`と`DayOfYear`の相関を計算すると、約`-0.27`の値が得られます。これは、予測モデルをトレーニングする意味があることを示しています。 @@ -226,7 +217,7 @@ plt.scatter(X_test,y_test) plt.plot(X_test,pred) ``` -線形回帰 +線形回帰 ## 多項式回帰 @@ -255,7 +246,7 @@ pipeline.fit(X_train,y_train) パイプラインは、元の`LinearRegression`オブジェクトと同じ方法で使用できます。つまり、パイプラインを`fit`し、その後`predict`を使用して予測結果を取得できます。以下はテストデータと近似曲線を示すグラフです： -多項式回帰 +多項式回帰 多項式回帰を使用することで、MSEをわずかに低下させ、決定係数をわずかに向上させることができますが、大きな改善はありません。他の特徴を考慮する必要があります！ @@ -273,7 +264,7 @@ pipeline.fit(X_train,y_train) 以下は、種類ごとの平均価格がどのように依存しているかを示しています： -種類ごとの平均価格 +種類ごとの平均価格 種類を考慮するためには、まずそれを数値形式に変換する必要があります。これを**エンコード**と呼びます。いくつかの方法があります： diff --git a/translations/ja/2-Regression/3-Linear/assignment.md b/translations/ja/2-Regression/3-Linear/assignment.md index 3d4e55dc0..0c085ced0 100644 --- a/translations/ja/2-Regression/3-Linear/assignment.md +++ b/translations/ja/2-Regression/3-Linear/assignment.md @@ -1,12 +1,3 @@ - # 回帰モデルを作成する ## 手順 diff --git a/translations/ja/2-Regression/3-Linear/solution/Julia/README.md b/translations/ja/2-Regression/3-Linear/solution/Julia/README.md index 655b6bd34..d94db2d31 100644 --- a/translations/ja/2-Regression/3-Linear/solution/Julia/README.md +++ b/translations/ja/2-Regression/3-Linear/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ja/2-Regression/4-Logistic/README.md b/translations/ja/2-Regression/4-Logistic/README.md index ff5096b58..bbd7c86b7 100644 --- a/translations/ja/2-Regression/4-Logistic/README.md +++ b/translations/ja/2-Regression/4-Logistic/README.md @@ -1,12 +1,3 @@ - # カテゴリー予測のためのロジスティック回帰 ![ロジスティック回帰と線形回帰のインフォグラフィック](../../../../2-Regression/4-Logistic/images/linear-vs-logistic.png) diff --git a/translations/ja/2-Regression/4-Logistic/assignment.md b/translations/ja/2-Regression/4-Logistic/assignment.md index 5f49499f8..65b537ceb 100644 --- a/translations/ja/2-Regression/4-Logistic/assignment.md +++ b/translations/ja/2-Regression/4-Logistic/assignment.md @@ -1,12 +1,3 @@ - # 回帰の再試行 ## 手順 diff --git a/translations/ja/2-Regression/4-Logistic/solution/Julia/README.md b/translations/ja/2-Regression/4-Logistic/solution/Julia/README.md index 07c4706e8..f03ef5730 100644 --- a/translations/ja/2-Regression/4-Logistic/solution/Julia/README.md +++ b/translations/ja/2-Regression/4-Logistic/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ja/2-Regression/README.md b/translations/ja/2-Regression/README.md index 24438b6eb..7703f3b40 100644 --- a/translations/ja/2-Regression/README.md +++ b/translations/ja/2-Regression/README.md @@ -1,12 +1,3 @@ - # 機械学習の回帰モデル ## 地域トピック: 北米におけるカボチャ価格の回帰モデル 🎃 diff --git a/translations/ja/3-Web-App/1-Web-App/README.md b/translations/ja/3-Web-App/1-Web-App/README.md index 2ec56f025..df8a94776 100644 --- a/translations/ja/3-Web-App/1-Web-App/README.md +++ b/translations/ja/3-Web-App/1-Web-App/README.md @@ -1,12 +1,3 @@ - # Webアプリで機械学習モデルを活用する このレッスンでは、機械学習モデルをトレーニングし、ユニークなデータセットを使用します。それは、_過去100年間のUFO目撃情報_ であり、NUFORCのデータベースから取得されたものです。 diff --git a/translations/ja/3-Web-App/1-Web-App/assignment.md b/translations/ja/3-Web-App/1-Web-App/assignment.md index 188e50c69..1467612f2 100644 --- a/translations/ja/3-Web-App/1-Web-App/assignment.md +++ b/translations/ja/3-Web-App/1-Web-App/assignment.md @@ -1,12 +1,3 @@ - # 別のモデルを試す ## 手順 diff --git a/translations/ja/3-Web-App/README.md b/translations/ja/3-Web-App/README.md index 11dfee418..37bd5e800 100644 --- a/translations/ja/3-Web-App/README.md +++ b/translations/ja/3-Web-App/README.md @@ -1,12 +1,3 @@ - # 機械学習モデルを活用したウェブアプリの構築 このカリキュラムのセクションでは、応用的な機械学習のトピックについて学びます。具体的には、Scikit-learnモデルをファイルとして保存し、それをウェブアプリケーション内で予測に使用する方法です。モデルを保存した後、Flaskで構築されたウェブアプリでそのモデルを使用する方法を学びます。まず、UFO目撃情報に関するデータを使用してモデルを作成します。その後、緯度と経度の値と秒数を入力することで、どの国がUFOを目撃したかを予測するウェブアプリを構築します。 diff --git a/translations/ja/4-Classification/1-Introduction/README.md b/translations/ja/4-Classification/1-Introduction/README.md index cd5f2abf6..f30159187 100644 --- a/translations/ja/4-Classification/1-Introduction/README.md +++ b/translations/ja/4-Classification/1-Introduction/README.md @@ -1,12 +1,3 @@ - # 分類の紹介 この4つのレッスンでは、古典的な機械学習の基本的な焦点である_分類_について探求します。アジアとインドの素晴らしい料理に関するデータセットを使い、さまざまな分類アルゴリズムを実践していきます。お腹が空いてきましたか？ diff --git a/translations/ja/4-Classification/1-Introduction/assignment.md b/translations/ja/4-Classification/1-Introduction/assignment.md index ec2f88b5a..91f84bb34 100644 --- a/translations/ja/4-Classification/1-Introduction/assignment.md +++ b/translations/ja/4-Classification/1-Introduction/assignment.md @@ -1,12 +1,3 @@ - # 分類方法を探る ## 手順 diff --git a/translations/ja/4-Classification/1-Introduction/solution/Julia/README.md b/translations/ja/4-Classification/1-Introduction/solution/Julia/README.md index d385b95be..34195cbad 100644 --- a/translations/ja/4-Classification/1-Introduction/solution/Julia/README.md +++ b/translations/ja/4-Classification/1-Introduction/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ja/4-Classification/2-Classifiers-1/README.md b/translations/ja/4-Classification/2-Classifiers-1/README.md index e793c542b..791fced77 100644 --- a/translations/ja/4-Classification/2-Classifiers-1/README.md +++ b/translations/ja/4-Classification/2-Classifiers-1/README.md @@ -1,12 +1,3 @@ - # 料理分類器 1 このレッスンでは、前回のレッスンで保存した、料理に関するバランスの取れたクリーンなデータセットを使用します。 diff --git a/translations/ja/4-Classification/2-Classifiers-1/assignment.md b/translations/ja/4-Classification/2-Classifiers-1/assignment.md index 067b9f4e2..5fe33cc94 100644 --- a/translations/ja/4-Classification/2-Classifiers-1/assignment.md +++ b/translations/ja/4-Classification/2-Classifiers-1/assignment.md @@ -1,12 +1,3 @@ - # ソルバーを学ぶ ## 指示 diff --git a/translations/ja/4-Classification/2-Classifiers-1/solution/Julia/README.md b/translations/ja/4-Classification/2-Classifiers-1/solution/Julia/README.md index ef7b0c198..8a6309a3c 100644 --- a/translations/ja/4-Classification/2-Classifiers-1/solution/Julia/README.md +++ b/translations/ja/4-Classification/2-Classifiers-1/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ja/4-Classification/3-Classifiers-2/README.md b/translations/ja/4-Classification/3-Classifiers-2/README.md index 45cf5a69f..d101d4e2d 100644 --- a/translations/ja/4-Classification/3-Classifiers-2/README.md +++ b/translations/ja/4-Classification/3-Classifiers-2/README.md @@ -1,12 +1,3 @@ - # 料理分類器 2 この第2回目の分類レッスンでは、数値データを分類するさまざまな方法を探ります。また、どの分類器を選ぶかによる影響についても学びます。 diff --git a/translations/ja/4-Classification/3-Classifiers-2/assignment.md b/translations/ja/4-Classification/3-Classifiers-2/assignment.md index 3fc442935..c6c39e5e4 100644 --- a/translations/ja/4-Classification/3-Classifiers-2/assignment.md +++ b/translations/ja/4-Classification/3-Classifiers-2/assignment.md @@ -1,12 +1,3 @@ - # パラメータプレイ ## 手順 diff --git a/translations/ja/4-Classification/3-Classifiers-2/solution/Julia/README.md b/translations/ja/4-Classification/3-Classifiers-2/solution/Julia/README.md index af45e44d7..e6ac43c7e 100644 --- a/translations/ja/4-Classification/3-Classifiers-2/solution/Julia/README.md +++ b/translations/ja/4-Classification/3-Classifiers-2/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ja/4-Classification/4-Applied/README.md b/translations/ja/4-Classification/4-Applied/README.md index 8264560e3..e24619427 100644 --- a/translations/ja/4-Classification/4-Applied/README.md +++ b/translations/ja/4-Classification/4-Applied/README.md @@ -1,12 +1,3 @@ - # 料理推薦ウェブアプリを作成する このレッスンでは、これまでのレッスンで学んだ技術を活用し、美味しい料理データセットを使用して分類モデルを構築します。また、保存したモデルを使用する小さなウェブアプリを作成し、Onnxのウェブランタイムを活用します。 diff --git a/translations/ja/4-Classification/4-Applied/assignment.md b/translations/ja/4-Classification/4-Applied/assignment.md index 532d4ea66..7656c4c18 100644 --- a/translations/ja/4-Classification/4-Applied/assignment.md +++ b/translations/ja/4-Classification/4-Applied/assignment.md @@ -1,12 +1,3 @@ - # レコメンダーを作成する ## 手順 diff --git a/translations/ja/4-Classification/README.md b/translations/ja/4-Classification/README.md index 1896cf7bc..9ba2532b7 100644 --- a/translations/ja/4-Classification/README.md +++ b/translations/ja/4-Classification/README.md @@ -1,12 +1,3 @@ - # 分類の始め方 ## 地域のトピック: 美味しいアジアとインド料理 🍜 diff --git a/translations/ja/5-Clustering/1-Visualize/README.md b/translations/ja/5-Clustering/1-Visualize/README.md index 52d433cc5..ed2a0c904 100644 --- a/translations/ja/5-Clustering/1-Visualize/README.md +++ b/translations/ja/5-Clustering/1-Visualize/README.md @@ -1,12 +1,3 @@ - # クラスタリングの紹介 クラスタリングは、[教師なし学習](https://wikipedia.org/wiki/Unsupervised_learning)の一種で、データセットがラベル付けされていない、または入力が事前定義された出力と一致していないことを前提としています。さまざまなアルゴリズムを使用してラベル付けされていないデータを分類し、データ内で認識されるパターンに基づいてグループ化を提供します。 diff --git a/translations/ja/5-Clustering/1-Visualize/assignment.md b/translations/ja/5-Clustering/1-Visualize/assignment.md index 53d91c965..aad535ec5 100644 --- a/translations/ja/5-Clustering/1-Visualize/assignment.md +++ b/translations/ja/5-Clustering/1-Visualize/assignment.md @@ -1,12 +1,3 @@ - # クラスタリングのための他の可視化方法を調査する ## 指示 diff --git a/translations/ja/5-Clustering/1-Visualize/solution/Julia/README.md b/translations/ja/5-Clustering/1-Visualize/solution/Julia/README.md index f6aa858d8..55517e1e8 100644 --- a/translations/ja/5-Clustering/1-Visualize/solution/Julia/README.md +++ b/translations/ja/5-Clustering/1-Visualize/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ja/5-Clustering/2-K-Means/README.md b/translations/ja/5-Clustering/2-K-Means/README.md index e9f65a177..e6eac49f3 100644 --- a/translations/ja/5-Clustering/2-K-Means/README.md +++ b/translations/ja/5-Clustering/2-K-Means/README.md @@ -1,12 +1,3 @@ - # K-Meansクラスタリング ## [事前クイズ](https://ff-quizzes.netlify.app/en/ml/) diff --git a/translations/ja/5-Clustering/2-K-Means/assignment.md b/translations/ja/5-Clustering/2-K-Means/assignment.md index 662c87573..5ce3d0806 100644 --- a/translations/ja/5-Clustering/2-K-Means/assignment.md +++ b/translations/ja/5-Clustering/2-K-Means/assignment.md @@ -1,12 +1,3 @@ - # 異なるクラスタリング手法を試す ## 手順 diff --git a/translations/ja/5-Clustering/2-K-Means/solution/Julia/README.md b/translations/ja/5-Clustering/2-K-Means/solution/Julia/README.md index 2001df1ce..3500be995 100644 --- a/translations/ja/5-Clustering/2-K-Means/solution/Julia/README.md +++ b/translations/ja/5-Clustering/2-K-Means/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ja/5-Clustering/README.md b/translations/ja/5-Clustering/README.md index d3029e5b5..fa5e90dde 100644 --- a/translations/ja/5-Clustering/README.md +++ b/translations/ja/5-Clustering/README.md @@ -1,12 +1,3 @@ - # 機械学習のためのクラスタリングモデル クラスタリングは、互いに似ているオブジェクトを見つけ、それらをクラスタと呼ばれるグループにまとめる機械学習のタスクです。他の機械学習アプローチとクラスタリングの違いは、プロセスが自動的に進む点です。実際、教師あり学習とは正反対と言っても良いでしょう。 diff --git a/translations/ja/6-NLP/1-Introduction-to-NLP/README.md b/translations/ja/6-NLP/1-Introduction-to-NLP/README.md index 7190e16c8..fe9867683 100644 --- a/translations/ja/6-NLP/1-Introduction-to-NLP/README.md +++ b/translations/ja/6-NLP/1-Introduction-to-NLP/README.md @@ -1,12 +1,3 @@ - # 自然言語処理の紹介 このレッスンでは、*計算言語学*の一分野である*自然言語処理*の簡単な歴史と重要な概念について学びます。 diff --git a/translations/ja/6-NLP/1-Introduction-to-NLP/assignment.md b/translations/ja/6-NLP/1-Introduction-to-NLP/assignment.md index 178e5ef73..5d43f9859 100644 --- a/translations/ja/6-NLP/1-Introduction-to-NLP/assignment.md +++ b/translations/ja/6-NLP/1-Introduction-to-NLP/assignment.md @@ -1,12 +1,3 @@ - # ボットを探そう ## 手順 diff --git a/translations/ja/6-NLP/2-Tasks/README.md b/translations/ja/6-NLP/2-Tasks/README.md index f2ef058c6..075bd71ca 100644 --- a/translations/ja/6-NLP/2-Tasks/README.md +++ b/translations/ja/6-NLP/2-Tasks/README.md @@ -1,12 +1,3 @@ - # 自然言語処理の一般的なタスクと技術 ほとんどの*自然言語処理*タスクでは、処理対象のテキストを分解し、分析し、その結果をルールやデータセットと照合する必要があります。これらのタスクを通じて、プログラマーはテキスト内の単語やフレーズの_意味_や_意図_、または単に_頻度_を導き出すことができます。 diff --git a/translations/ja/6-NLP/2-Tasks/assignment.md b/translations/ja/6-NLP/2-Tasks/assignment.md index 6b0094799..3ceada364 100644 --- a/translations/ja/6-NLP/2-Tasks/assignment.md +++ b/translations/ja/6-NLP/2-Tasks/assignment.md @@ -1,12 +1,3 @@ - # ボットに会話をさせる ## 手順 diff --git a/translations/ja/6-NLP/3-Translation-Sentiment/README.md b/translations/ja/6-NLP/3-Translation-Sentiment/README.md index bd46760d8..4b923ef25 100644 --- a/translations/ja/6-NLP/3-Translation-Sentiment/README.md +++ b/translations/ja/6-NLP/3-Translation-Sentiment/README.md @@ -1,12 +1,3 @@ - # 翻訳と感情分析をMLで行う 前のレッスンでは、`TextBlob`を使用して基本的なボットを構築する方法を学びました。このライブラリは、名詞句の抽出などの基本的な自然言語処理（NLP）タスクを実行するために、裏で機械学習（ML）を組み込んでいます。計算言語学におけるもう一つの重要な課題は、ある話し言葉や書き言葉の言語から別の言語への正確な「翻訳」です。 diff --git a/translations/ja/6-NLP/3-Translation-Sentiment/assignment.md b/translations/ja/6-NLP/3-Translation-Sentiment/assignment.md index 1946ed95e..c386e627b 100644 --- a/translations/ja/6-NLP/3-Translation-Sentiment/assignment.md +++ b/translations/ja/6-NLP/3-Translation-Sentiment/assignment.md @@ -1,12 +1,3 @@ - # 詩的ライセンス ## 手順 diff --git a/translations/ja/6-NLP/3-Translation-Sentiment/solution/Julia/README.md b/translations/ja/6-NLP/3-Translation-Sentiment/solution/Julia/README.md index b14ee641d..75292d14d 100644 --- a/translations/ja/6-NLP/3-Translation-Sentiment/solution/Julia/README.md +++ b/translations/ja/6-NLP/3-Translation-Sentiment/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ja/6-NLP/3-Translation-Sentiment/solution/R/README.md b/translations/ja/6-NLP/3-Translation-Sentiment/solution/R/README.md index 69160a871..d85cd01fd 100644 --- a/translations/ja/6-NLP/3-Translation-Sentiment/solution/R/README.md +++ b/translations/ja/6-NLP/3-Translation-Sentiment/solution/R/README.md @@ -1,12 +1,3 @@ - これは一時的なプレースホルダーです --- diff --git a/translations/ja/6-NLP/4-Hotel-Reviews-1/README.md b/translations/ja/6-NLP/4-Hotel-Reviews-1/README.md index f61e7b946..f40645ec3 100644 --- a/translations/ja/6-NLP/4-Hotel-Reviews-1/README.md +++ b/translations/ja/6-NLP/4-Hotel-Reviews-1/README.md @@ -1,12 +1,3 @@ - # ホテルレビューによる感情分析 - データの処理 このセクションでは、前のレッスンで学んだ技術を使って、大規模なデータセットの探索的データ分析を行います。各列の有用性を十分に理解した後、以下を学びます： diff --git a/translations/ja/6-NLP/4-Hotel-Reviews-1/assignment.md b/translations/ja/6-NLP/4-Hotel-Reviews-1/assignment.md index a51889432..160a05d10 100644 --- a/translations/ja/6-NLP/4-Hotel-Reviews-1/assignment.md +++ b/translations/ja/6-NLP/4-Hotel-Reviews-1/assignment.md @@ -1,12 +1,3 @@ - # NLTK ## 手順 diff --git a/translations/ja/6-NLP/4-Hotel-Reviews-1/solution/Julia/README.md b/translations/ja/6-NLP/4-Hotel-Reviews-1/solution/Julia/README.md index 5f48609cf..cfc9e257a 100644 --- a/translations/ja/6-NLP/4-Hotel-Reviews-1/solution/Julia/README.md +++ b/translations/ja/6-NLP/4-Hotel-Reviews-1/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ja/6-NLP/4-Hotel-Reviews-1/solution/R/README.md b/translations/ja/6-NLP/4-Hotel-Reviews-1/solution/R/README.md index a5808376e..28bd913a4 100644 --- a/translations/ja/6-NLP/4-Hotel-Reviews-1/solution/R/README.md +++ b/translations/ja/6-NLP/4-Hotel-Reviews-1/solution/R/README.md @@ -1,12 +1,3 @@ - これは一時的なプレースホルダーです --- diff --git a/translations/ja/6-NLP/5-Hotel-Reviews-2/README.md b/translations/ja/6-NLP/5-Hotel-Reviews-2/README.md index 85af9b263..baf6c9a04 100644 --- a/translations/ja/6-NLP/5-Hotel-Reviews-2/README.md +++ b/translations/ja/6-NLP/5-Hotel-Reviews-2/README.md @@ -1,12 +1,3 @@ - # ホテルレビューを用いた感情分析 データセットを詳細に調査した後は、列をフィルタリングし、NLP技術を使用してホテルに関する新たな洞察を得る時です。 diff --git a/translations/ja/6-NLP/5-Hotel-Reviews-2/assignment.md b/translations/ja/6-NLP/5-Hotel-Reviews-2/assignment.md index 0af761f5a..eea6237cc 100644 --- a/translations/ja/6-NLP/5-Hotel-Reviews-2/assignment.md +++ b/translations/ja/6-NLP/5-Hotel-Reviews-2/assignment.md @@ -1,12 +1,3 @@ - # 別のデータセットを試してみよう ## 手順 diff --git a/translations/ja/6-NLP/5-Hotel-Reviews-2/solution/Julia/README.md b/translations/ja/6-NLP/5-Hotel-Reviews-2/solution/Julia/README.md index 650d2dd20..f98aabeca 100644 --- a/translations/ja/6-NLP/5-Hotel-Reviews-2/solution/Julia/README.md +++ b/translations/ja/6-NLP/5-Hotel-Reviews-2/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ja/6-NLP/5-Hotel-Reviews-2/solution/R/README.md b/translations/ja/6-NLP/5-Hotel-Reviews-2/solution/R/README.md index e288d7eb8..05912c11c 100644 --- a/translations/ja/6-NLP/5-Hotel-Reviews-2/solution/R/README.md +++ b/translations/ja/6-NLP/5-Hotel-Reviews-2/solution/R/README.md @@ -1,12 +1,3 @@ - これは一時的なプレースホルダーです --- diff --git a/translations/ja/6-NLP/README.md b/translations/ja/6-NLP/README.md index 5d4de3f95..93bed5ea1 100644 --- a/translations/ja/6-NLP/README.md +++ b/translations/ja/6-NLP/README.md @@ -1,12 +1,3 @@ - # 自然言語処理の始め方 自然言語処理（NLP）は、コンピュータプログラムが話し言葉や書き言葉としての人間の言語を理解する能力を指します。これを自然言語と呼びます。NLPは人工知能（AI）の一部であり、50年以上の歴史を持ち、言語学の分野にルーツがあります。この分野全体は、機械が人間の言語を理解し処理するのを助けることを目的としています。そして、スペルチェックや機械翻訳のようなタスクを実行するために使用されます。医療研究、検索エンジン、ビジネスインテリジェンスなど、さまざまな分野で実際の応用例があります。 diff --git a/translations/ja/6-NLP/data/README.md b/translations/ja/6-NLP/data/README.md index 16de19987..9f47fa4ca 100644 --- a/translations/ja/6-NLP/data/README.md +++ b/translations/ja/6-NLP/data/README.md @@ -1,12 +1,3 @@ - このフォルダーにホテルレビューのデータをダウンロードしてください。 --- diff --git a/translations/ja/7-TimeSeries/1-Introduction/README.md b/translations/ja/7-TimeSeries/1-Introduction/README.md index 73b653ef3..15a8f01e3 100644 --- a/translations/ja/7-TimeSeries/1-Introduction/README.md +++ b/translations/ja/7-TimeSeries/1-Introduction/README.md @@ -1,12 +1,3 @@ - # 時系列予測の入門 ![時系列の概要をスケッチノートで表現](../../../../sketchnotes/ml-timeseries.png) diff --git a/translations/ja/7-TimeSeries/1-Introduction/assignment.md b/translations/ja/7-TimeSeries/1-Introduction/assignment.md index e1b179c1e..dede74592 100644 --- a/translations/ja/7-TimeSeries/1-Introduction/assignment.md +++ b/translations/ja/7-TimeSeries/1-Introduction/assignment.md @@ -1,12 +1,3 @@ - # 時系列データをさらに可視化する ## 手順 diff --git a/translations/ja/7-TimeSeries/1-Introduction/solution/Julia/README.md b/translations/ja/7-TimeSeries/1-Introduction/solution/Julia/README.md index b98751696..b4179241b 100644 --- a/translations/ja/7-TimeSeries/1-Introduction/solution/Julia/README.md +++ b/translations/ja/7-TimeSeries/1-Introduction/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ja/7-TimeSeries/1-Introduction/solution/R/README.md b/translations/ja/7-TimeSeries/1-Introduction/solution/R/README.md index 090d62cba..92820b4b7 100644 --- a/translations/ja/7-TimeSeries/1-Introduction/solution/R/README.md +++ b/translations/ja/7-TimeSeries/1-Introduction/solution/R/README.md @@ -1,12 +1,3 @@ - これは一時的なプレースホルダー --- diff --git a/translations/ja/7-TimeSeries/2-ARIMA/README.md b/translations/ja/7-TimeSeries/2-ARIMA/README.md index 4519090da..d7916e4fe 100644 --- a/translations/ja/7-TimeSeries/2-ARIMA/README.md +++ b/translations/ja/7-TimeSeries/2-ARIMA/README.md @@ -1,12 +1,3 @@ - # ARIMAによる時系列予測 前のレッスンでは、時系列予測について少し学び、一定期間にわたる電力負荷の変動を示すデータセットを読み込みました。 diff --git a/translations/ja/7-TimeSeries/2-ARIMA/assignment.md b/translations/ja/7-TimeSeries/2-ARIMA/assignment.md index ba1bc3d05..063a53d73 100644 --- a/translations/ja/7-TimeSeries/2-ARIMA/assignment.md +++ b/translations/ja/7-TimeSeries/2-ARIMA/assignment.md @@ -1,12 +1,3 @@ - # 新しいARIMAモデル ## 手順 diff --git a/translations/ja/7-TimeSeries/2-ARIMA/solution/Julia/README.md b/translations/ja/7-TimeSeries/2-ARIMA/solution/Julia/README.md index c6439336a..6c5b00136 100644 --- a/translations/ja/7-TimeSeries/2-ARIMA/solution/Julia/README.md +++ b/translations/ja/7-TimeSeries/2-ARIMA/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ja/7-TimeSeries/2-ARIMA/solution/R/README.md b/translations/ja/7-TimeSeries/2-ARIMA/solution/R/README.md index 9e07253e3..623be5702 100644 --- a/translations/ja/7-TimeSeries/2-ARIMA/solution/R/README.md +++ b/translations/ja/7-TimeSeries/2-ARIMA/solution/R/README.md @@ -1,12 +1,3 @@ - これは一時的なプレースホルダー --- diff --git a/translations/ja/7-TimeSeries/3-SVR/README.md b/translations/ja/7-TimeSeries/3-SVR/README.md index 451057cc4..10e03f393 100644 --- a/translations/ja/7-TimeSeries/3-SVR/README.md +++ b/translations/ja/7-TimeSeries/3-SVR/README.md @@ -1,12 +1,3 @@ - # サポートベクター回帰による時系列予測 前回のレッスンでは、ARIMAモデルを使用して時系列予測を行う方法を学びました。今回は、連続データを予測するために使用される回帰モデルであるサポートベクター回帰（Support Vector Regressor）モデルについて学びます。 diff --git a/translations/ja/7-TimeSeries/3-SVR/assignment.md b/translations/ja/7-TimeSeries/3-SVR/assignment.md index 2476c7fd1..64266f9db 100644 --- a/translations/ja/7-TimeSeries/3-SVR/assignment.md +++ b/translations/ja/7-TimeSeries/3-SVR/assignment.md @@ -1,12 +1,3 @@ - # 新しいSVRモデル ## 手順 [^1] diff --git a/translations/ja/7-TimeSeries/README.md b/translations/ja/7-TimeSeries/README.md index 4abe44300..3ed824cb2 100644 --- a/translations/ja/7-TimeSeries/README.md +++ b/translations/ja/7-TimeSeries/README.md @@ -1,12 +1,3 @@ - # 時系列予測の入門 時系列予測とは何でしょうか？過去の傾向を分析することで未来の出来事を予測することです。 diff --git a/translations/ja/8-Reinforcement/1-QLearning/README.md b/translations/ja/8-Reinforcement/1-QLearning/README.md index efd479bc4..ec331534f 100644 --- a/translations/ja/8-Reinforcement/1-QLearning/README.md +++ b/translations/ja/8-Reinforcement/1-QLearning/README.md @@ -1,12 +1,3 @@ - # 強化学習とQ学習の入門 ![機械学習における強化学習の概要をスケッチノートで表現](../../../../sketchnotes/ml-reinforcement.png) diff --git a/translations/ja/8-Reinforcement/1-QLearning/assignment.md b/translations/ja/8-Reinforcement/1-QLearning/assignment.md index c77669dbf..c05b9d7d2 100644 --- a/translations/ja/8-Reinforcement/1-QLearning/assignment.md +++ b/translations/ja/8-Reinforcement/1-QLearning/assignment.md @@ -1,12 +1,3 @@ - # より現実的な世界 私たちの状況では、ピーターはほとんど疲れたり空腹になったりすることなく移動することができました。しかし、より現実的な世界では、ピーターは時々座って休む必要があり、また食事を取る必要があります。以下のルールを実装することで、私たちの世界をより現実的にしてみましょう。 diff --git a/translations/ja/8-Reinforcement/1-QLearning/solution/Julia/README.md b/translations/ja/8-Reinforcement/1-QLearning/solution/Julia/README.md index a98bceafa..671021629 100644 --- a/translations/ja/8-Reinforcement/1-QLearning/solution/Julia/README.md +++ b/translations/ja/8-Reinforcement/1-QLearning/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ja/8-Reinforcement/1-QLearning/solution/R/README.md b/translations/ja/8-Reinforcement/1-QLearning/solution/R/README.md index f45e88a7e..b4865a276 100644 --- a/translations/ja/8-Reinforcement/1-QLearning/solution/R/README.md +++ b/translations/ja/8-Reinforcement/1-QLearning/solution/R/README.md @@ -1,12 +1,3 @@ - これは一時的なプレースホルダー --- diff --git a/translations/ja/8-Reinforcement/2-Gym/README.md b/translations/ja/8-Reinforcement/2-Gym/README.md index 381026157..6fac61c5b 100644 --- a/translations/ja/8-Reinforcement/2-Gym/README.md +++ b/translations/ja/8-Reinforcement/2-Gym/README.md @@ -1,12 +1,3 @@ - ## 前提条件 このレッスンでは、**OpenAI Gym**というライブラリを使用して、さまざまな**環境**をシミュレーションします。このレッスンのコードはローカル環境（例: Visual Studio Code）で実行することができ、その場合シミュレーションは新しいウィンドウで開きます。オンラインでコードを実行する場合は、[こちら](https://towardsdatascience.com/rendering-openai-gym-envs-on-binder-and-google-colab-536f99391cc7)に記載されているように、コードにいくつかの調整が必要になる場合があります。 diff --git a/translations/ja/8-Reinforcement/2-Gym/assignment.md b/translations/ja/8-Reinforcement/2-Gym/assignment.md index 93d5839f8..aaa3eb954 100644 --- a/translations/ja/8-Reinforcement/2-Gym/assignment.md +++ b/translations/ja/8-Reinforcement/2-Gym/assignment.md @@ -1,12 +1,3 @@ - # 山登りカーを訓練する [OpenAI Gym](http://gym.openai.com) は、すべての環境が同じAPIを提供するように設計されています。つまり、`reset`、`step`、`render`という同じメソッドと、**アクションスペース**および**観測スペース**の同じ抽象化を備えています。そのため、最小限のコード変更で異なる環境に同じ強化学習アルゴリズムを適用することが可能です。 diff --git a/translations/ja/8-Reinforcement/2-Gym/solution/Julia/README.md b/translations/ja/8-Reinforcement/2-Gym/solution/Julia/README.md index 1cbfdf04f..4775bd36c 100644 --- a/translations/ja/8-Reinforcement/2-Gym/solution/Julia/README.md +++ b/translations/ja/8-Reinforcement/2-Gym/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ja/8-Reinforcement/2-Gym/solution/R/README.md b/translations/ja/8-Reinforcement/2-Gym/solution/R/README.md index f852cfd5e..6e677aa71 100644 --- a/translations/ja/8-Reinforcement/2-Gym/solution/R/README.md +++ b/translations/ja/8-Reinforcement/2-Gym/solution/R/README.md @@ -1,12 +1,3 @@ - これは一時的なプレースホルダー --- diff --git a/translations/ja/8-Reinforcement/README.md b/translations/ja/8-Reinforcement/README.md index bc225c820..ab881e60d 100644 --- a/translations/ja/8-Reinforcement/README.md +++ b/translations/ja/8-Reinforcement/README.md @@ -1,12 +1,3 @@ - # 強化学習の紹介 強化学習（RL）は、教師あり学習や教師なし学習と並ぶ基本的な機械学習のパラダイムの一つとされています。RLは意思決定に関するものであり、正しい決定を下す、または少なくともそこから学ぶことを目指します。 diff --git a/translations/ja/9-Real-World/1-Applications/README.md b/translations/ja/9-Real-World/1-Applications/README.md index feb840798..21afc9468 100644 --- a/translations/ja/9-Real-World/1-Applications/README.md +++ b/translations/ja/9-Real-World/1-Applications/README.md @@ -1,12 +1,3 @@ - # 後書き: 実世界における機械学習 ![実世界における機械学習の概要をスケッチノートで表現](../../../../sketchnotes/ml-realworld.png) diff --git a/translations/ja/9-Real-World/1-Applications/assignment.md b/translations/ja/9-Real-World/1-Applications/assignment.md index 5bb2c1886..713195154 100644 --- a/translations/ja/9-Real-World/1-Applications/assignment.md +++ b/translations/ja/9-Real-World/1-Applications/assignment.md @@ -1,12 +1,3 @@ - # 機械学習スカベンジャーハント ## 指示 diff --git a/translations/ja/9-Real-World/2-Debugging-ML-Models/README.md b/translations/ja/9-Real-World/2-Debugging-ML-Models/README.md index 85805ed4f..f41707f50 100644 --- a/translations/ja/9-Real-World/2-Debugging-ML-Models/README.md +++ b/translations/ja/9-Real-World/2-Debugging-ML-Models/README.md @@ -1,12 +1,3 @@ - # 後書き: 責任あるAIダッシュボードコンポーネントを使用した機械学習モデルのデバッグ ## [講義前クイズ](https://ff-quizzes.netlify.app/en/ml/) diff --git a/translations/ja/9-Real-World/2-Debugging-ML-Models/assignment.md b/translations/ja/9-Real-World/2-Debugging-ML-Models/assignment.md index aece0a9d7..d542865d5 100644 --- a/translations/ja/9-Real-World/2-Debugging-ML-Models/assignment.md +++ b/translations/ja/9-Real-World/2-Debugging-ML-Models/assignment.md @@ -1,12 +1,3 @@ - # 責任あるAI（RAI）ダッシュボードを探る ## 手順 diff --git a/translations/ja/9-Real-World/README.md b/translations/ja/9-Real-World/README.md index fc8c5f2e3..f8b84a876 100644 --- a/translations/ja/9-Real-World/README.md +++ b/translations/ja/9-Real-World/README.md @@ -1,12 +1,3 @@ - # 後書き: 古典的機械学習の実世界での応用 このカリキュラムのこのセクションでは、古典的な機械学習の実世界での応用例を紹介します。インターネットを徹底的に調査し、ニューラルネットワークやディープラーニング、AIをできるだけ避けた上で、これらの戦略を使用した応用に関するホワイトペーパーや記事を見つけました。機械学習がビジネスシステム、生態学的応用、金融、芸術や文化などでどのように活用されているかを学びましょう。 diff --git a/translations/ja/AGENTS.md b/translations/ja/AGENTS.md index 2bc067690..8584c1071 100644 --- a/translations/ja/AGENTS.md +++ b/translations/ja/AGENTS.md @@ -1,12 +1,3 @@ - # AGENTS.md ## プロジェクト概要 diff --git a/translations/ja/CODE_OF_CONDUCT.md b/translations/ja/CODE_OF_CONDUCT.md index 0950820eb..6c6b0eb56 100644 --- a/translations/ja/CODE_OF_CONDUCT.md +++ b/translations/ja/CODE_OF_CONDUCT.md @@ -1,12 +1,3 @@ - # Microsoft オープンソース行動規範 このプロジェクトは [Microsoft オープンソース行動規範](https://opensource.microsoft.com/codeofconduct/) を採用しています。 diff --git a/translations/ja/CONTRIBUTING.md b/translations/ja/CONTRIBUTING.md index 0adbee616..7ee9955e5 100644 --- a/translations/ja/CONTRIBUTING.md +++ b/translations/ja/CONTRIBUTING.md @@ -1,12 +1,3 @@ - # 貢献について このプロジェクトでは、貢献や提案を歓迎しています。ほとんどの貢献には、Contributor License Agreement (CLA) に同意する必要があります。CLAでは、あなたがその貢献を使用する権利を私たちに与える権利を持っていること、そして実際にその権利を与えることを宣言します。詳細については、https://cla.microsoft.com をご覧ください。 diff --git a/translations/ja/README.md b/translations/ja/README.md index a506b6564..e8547c5d1 100644 --- a/translations/ja/README.md +++ b/translations/ja/README.md @@ -1,12 +1,3 @@ - [![GitHub license](https://img.shields.io/github/license/microsoft/ML-For-Beginners.svg)](https://github.com/microsoft/ML-For-Beginners/blob/master/LICENSE) [![GitHub contributors](https://img.shields.io/github/contributors/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/graphs/contributors/) [![GitHub issues](https://img.shields.io/github/issues/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/issues/) @@ -17,79 +8,79 @@ CO_OP_TRANSLATOR_METADATA: [![GitHub forks](https://img.shields.io/github/forks/microsoft/ML-For-Beginners.svg?style=social&label=Fork)](https://GitHub.com/microsoft/ML-For-Beginners/network/) [![GitHub stars](https://img.shields.io/github/stars/microsoft/ML-For-Beginners.svg?style=social&label=Star)](https://GitHub.com/microsoft/ML-For-Beginners/stargazers/) -### 🌐 多言語対応 +### 🌐 多言語サポート -#### GitHub Action によるサポート（自動＆常に最新） +#### GitHub Actions による対応（自動化＆常に最新） -[Arabic](../ar/README.md) | [Bengali](../bn/README.md) | [Bulgarian](../bg/README.md) | [Burmese (Myanmar)](../my/README.md) | [Chinese (Simplified)](../zh/README.md) | [Chinese (Traditional, Hong Kong)](../hk/README.md) | [Chinese (Traditional, Macau)](../mo/README.md) | [Chinese (Traditional, Taiwan)](../tw/README.md) | [Croatian](../hr/README.md) | [Czech](../cs/README.md) | [Danish](../da/README.md) | [Dutch](../nl/README.md) | [Estonian](../et/README.md) | [Finnish](../fi/README.md) | [French](../fr/README.md) | [German](../de/README.md) | [Greek](../el/README.md) | [Hebrew](../he/README.md) | [Hindi](../hi/README.md) | [Hungarian](../hu/README.md) | [Indonesian](../id/README.md) | [Italian](../it/README.md) | [Japanese](./README.md) | [Kannada](../kn/README.md) | [Korean](../ko/README.md) | [Lithuanian](../lt/README.md) | [Malay](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepali](../ne/README.md) | [Nigerian Pidgin](../pcm/README.md) | [Norwegian](../no/README.md) | [Persian (Farsi)](../fa/README.md) | [Polish](../pl/README.md) | [Portuguese (Brazil)](../br/README.md) | [Portuguese (Portugal)](../pt/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Romanian](../ro/README.md) | [Russian](../ru/README.md) | [Serbian (Cyrillic)](../sr/README.md) | [Slovak](../sk/README.md) | [Slovenian](../sl/README.md) | [Spanish](../es/README.md) | [Swahili](../sw/README.md) | [Swedish](../sv/README.md) | [Tagalog (Filipino)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugu](../te/README.md) | [Thai](../th/README.md) | [Turkish](../tr/README.md) | [Ukrainian](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnamese](../vi/README.md) +[アラビア語](../ar/README.md) | [ベンガル語](../bn/README.md) | [ブルガリア語](../bg/README.md) | [ビルマ語（ミャンマー）](../my/README.md) | [中国語（簡体字）](../zh-CN/README.md) | [中国語（繁体字、香港）](../zh-HK/README.md) | [中国語（繁体字、マカオ）](../zh-MO/README.md) | [中国語（繁体字、台湾）](../zh-TW/README.md) | [クロアチア語](../hr/README.md) | [チェコ語](../cs/README.md) | [デンマーク語](../da/README.md) | [オランダ語](../nl/README.md) | [エストニア語](../et/README.md) | [フィンランド語](../fi/README.md) | [フランス語](../fr/README.md) | [ドイツ語](../de/README.md) | [ギリシャ語](../el/README.md) | [ヘブライ語](../he/README.md) | [ヒンディー語](../hi/README.md) | [ハンガリー語](../hu/README.md) | [インドネシア語](../id/README.md) | [イタリア語](../it/README.md) | [日本語](./README.md) | [カンナダ語](../kn/README.md) | [韓国語](../ko/README.md) | [リトアニア語](../lt/README.md) | [マレー語](../ms/README.md) | [マラヤーラム語](../ml/README.md) | [マラーティー語](../mr/README.md) | [ネパール語](../ne/README.md) | [ナイジェリア・ピジン英語](../pcm/README.md) | [ノルウェー語](../no/README.md) | [ペルシャ語（ファルシ）](../fa/README.md) | [ポーランド語](../pl/README.md) | [ポルトガル語（ブラジル）](../pt-BR/README.md) | [ポルトガル語（ポルトガル）](../pt-PT/README.md) | [パンジャブ語（グルムキー）](../pa/README.md) | [ルーマニア語](../ro/README.md) | [ロシア語](../ru/README.md) | [セルビア語（キリル）](../sr/README.md) | [スロバキア語](../sk/README.md) | [スロベニア語](../sl/README.md) | [スペイン語](../es/README.md) | [スワヒリ語](../sw/README.md) | [スウェーデン語](../sv/README.md) | [タガログ語（フィリピン）](../tl/README.md) | [タミル語](../ta/README.md) | [テルグ語](../te/README.md) | [タイ語](../th/README.md) | [トルコ語](../tr/README.md) | [ウクライナ語](../uk/README.md) | [ウルドゥー語](../ur/README.md) | [ベトナム語](../vi/README.md) -> **ローカルにクローンするのが好みですか？** +> **ローカルにクローンしたいですか？** -> このリポジトリには50以上の言語の翻訳が含まれており、ダウンロードサイズが大幅に増加します。翻訳なしでクローンするには、スパースチェックアウトを使用してください： +> このリポジトリには50以上の言語翻訳が含まれているため、ダウンロードサイズが大幅に増加します。翻訳なしでクローンしたい場合は、スパースチェックアウトを使用してください： > ```bash > git clone --filter=blob:none --sparse https://github.com/microsoft/ML-For-Beginners.git > cd ML-For-Beginners > git sparse-checkout set --no-cone '/*' '!translations' '!translated_images' > ``` -> これにより、コースを完了するために必要なすべてがより高速にダウンロードできます。 +> これにより、コースを完了するために必要なすべてをはるかに高速にダウンロードできます。 #### コミュニティに参加しよう [![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -私たちはDiscordでAIと共に学ぶシリーズを開催しています。詳細と参加はこちら：[Learn with AI Series](https://aka.ms/learnwithai/discord) （2025年9月18日～30日）。GitHub Copilotを活用したデータサイエンスのコツを学べます。 +Discordで学習シリーズを実施中です。詳細と参加は[Learn with AI Series](https://aka.ms/learnwithai/discord)で2025年9月18日〜30日まで。GitHub Copilotを使ったデータサイエンスのコツが学べます。 -![Learn with AI series](../../../../translated_images/ja/3.9b58fd8d6c373c20.webp) +![Learn with AI series](../../translated_images/ja/3.9b58fd8d6c373c20.webp) -# Machine Learning for Beginners - カリキュラム +# はじめてのための機械学習 - カリキュラム -> 🌍 世界の文化を通じて機械学習を探求する旅へようこそ 🌍 +> 🌍 世界の文化を巡りながら機械学習を学ぼう 🌍 -MicrosoftのCloud Advocatesは、**機械学習**に関する12週間・全26レッスンのカリキュラムを提供します。このカリキュラムでは、主にScikit-learnを使用し、深層学習を避ける「古典的な機械学習」と呼ばれるものを学びます。深層学習は私たちの[AI for Beginnersのカリキュラム](https://aka.ms/ai4beginners)で扱っています。また、[Data Science for Beginnersのカリキュラム](https://aka.ms/ds4beginners)と組み合わせるのもおすすめです。 +MicrosoftのCloud Advocatesは、12週間、26レッスンにわたる**機械学習**に関するカリキュラムを提供します。このカリキュラムでは主にScikit-learnを使い、「クラシック機械学習」と呼ばれることもある手法を学びます。ディープラーニングは[AI for Beginnersカリキュラム](https://aka.ms/ai4beginners)でカバーしています。さらに、[Data Science for Beginnersカリキュラム](https://aka.ms/ds4beginners)と組み合わせて学べます。 -世界各地のデータに古典的な手法を適用しながら旅をしましょう。各レッスンには事前・事後のクイズ、レッスン完了に必要な書面の指示、解答例、課題などが含まれます。プロジェクトベースの教育法により、学習しながら実際に作成し、スキルの習得を促進します。 +世界各地のデータにこのクラシックな手法を適用しながら旅をしましょう。それぞれのレッスンは事前・事後のクイズ、レッスンの指示、ソリューション、課題などを含みます。プロジェクトベースの教育法により、学びながら作ることで新しいスキルが定着します。 -**✍️ 執筆者の皆様に心から感謝します** Jen Looper、Stephen Howell、Francesca Lazzeri、Tomomi Imura、Cassie Breviu、Dmitry Soshnikov、Chris Noring、Anirban Mukherjee、Ornella Altunyan、Ruth Yakubu、Amy Boyd +**✍️ 著者の皆様に心から感謝** ジェン・ルーパー、スティーブン・ハウェル、フランチェスカ・ラゼリ、井村知美、キャシー・ブレビウ、ドミトリー・ソシニコフ、クリス・ノーリング、アニルバン・ムカジー、オルネラ・アルトゥニャン、ルース・ヤクブ、エイミー・ボイド -**🎨 イラスト作成に感謝** Tomomi Imura、Dasani Madipalli、Jen Looper +**🎨 イラストレーターの皆様にも感謝** 井村知美、ダサニ・マディパリ、ジェン・ルーパー -**🙏 特別な感謝 🙏 Microsoft Student Ambassadorの執筆者、レビュアー、コンテンツ寄稿者へ** 特にRishit Dagli、Muhammad Sakib Khan Inan、Rohan Raj、Alexandru Petrescu、Abhishek Jaiswal、Nawrin Tabassum、Ioan Samuila、Snigdha Agarwal +**🙏 特別な感謝 🙏 Microsoft Student Ambassador の著者、レビュアー、コンテンツ提供者の皆様へ** 特にリシット・ダグリ、ムハンマド・サキブ・カーン・イナン、ロハン・ラージ、アレクサンドル・ペトレスク、アビシェク・ジャイスワル、ナウリン・タバスム、イオアン・サムイラ、スニグダ・アガルワル -**🤩 Microsoft Student Ambassadors Eric Wanjau、Jasleen Sondhi、Vidushi Gupta に特別感謝！Rレッスンを担当** +**🤩 Microsoft Student Ambassadorsのエリック・ワンジャウ、ジャスリーン・ソンディ、ヴィドゥシ・グプタにも特別感謝、Rレッスンを担当！** -# 始め方 +# はじめに -次の手順に従ってください: -1. **リポジトリをフォーク**：このページ右上の「Fork」ボタンをクリック。 -2. **リポジトリをクローン**：`git clone https://github.com/microsoft/ML-For-Beginners.git` +以下の手順に従ってください： +1. **リポジトリをフォーク**: このページ右上の「Fork」ボタンをクリックします。 +2. **リポジトリをクローン**: `git clone https://github.com/microsoft/ML-For-Beginners.git` -> [このコースの追加リソースはMicrosoft Learnのコレクションにあります](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) +> [このコースに関する全追加リソースはMicrosoft Learnコレクションで見つけられます](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) -> 🔧 **困ったら？** [トラブルシューティングガイド](TROUBLESHOOTING.md)をご覧ください。インストール、セットアップ、レッスン実行のよくある問題の解決策を掲載しています。 +> 🔧 **困ったときは？** インストールやセットアップ、レッスン実行に関するよくある問題は[トラブルシューティングガイド](TROUBLESHOOTING.md)を参照してください。 -**[学生の皆様](https://aka.ms/student-page)**、このカリキュラムを利用するには、このリポジトリを自分のGitHubアカウントにフォークし、個人またはグループで演習を完了してください： +**[学生の皆さん](https://aka.ms/student-page)**、このカリキュラムを使うには、リポジトリを自分のGitHubアカウントにフォークし、グループまたは個人で課題を進めてください： -- 事前講義クイズから始める。 -- 講義を読み、各知識チェックで停止して理解を深めながらアクティビティを完了。 -- 解答コードを実行するよりも、レッスンを理解してプロジェクトを自作することに挑戦。解答コードは各プロジェクトレッスンの `/solution` フォルダにあります。 -- 事後講義クイズを受ける。 -- チャレンジを完了する。 -- 課題を完了する。 -- レッスングループを終えたら、[ディスカッションボード](https://github.com/microsoft/ML-For-Beginners/discussions)で適切なPATルーブリックを記入し「学びを声に出そう」。PAT（Progress Assessment Tool）は、学習の進捗を評価・強化するためのルーブリックです。他のPATにもリアクションし、共に学べます。 +- 事前のクイズから始めましょう。 +- レッスンを読んで活動を完了します。知識点ごとに立ち止まり、考えましょう。 +- ソリューションコードをそのまま動かすのではなく、理解しながらプロジェクトを作成に挑戦してください。ソリューションは各プロジェクトレッスンの`/solution`フォルダにあります。 +- 事後のクイズを受けましょう。 +- チャレンジに取り組みましょう。 +- 課題を完了しましょう。 +- レッスングループが完了したら、[ディスカッションボード](https://github.com/microsoft/ML-For-Beginners/discussions)で「アウトラウドラーニング（学びの声）」をPATルーブリックで投稿してください。‘PAT’は進捗評価ツールのことで、さらに学習を深めます。他のPATにもリアクションして、共に学びましょう。 -> さらに学習を深めるには、これらの[Microsoft Learn](https://docs.microsoft.com/en-us/users/jenlooper-2911/collections/k7o7tg1gp306q4?WT.mc_id=academic-77952-leestott)モジュールや学習パスの受講をおすすめします。 +> さらなる学習には、[Microsoft Learn](https://docs.microsoft.com/en-us/users/jenlooper-2911/collections/k7o7tg1gp306q4?WT.mc_id=academic-77952-leestott)のモジュールや学習パスをおすすめします。 -**先生方へ**、このカリキュラムの効果的な使い方についていくつかの[提案を用意しています](for-teachers.md)。 +**教員の皆様**には、このカリキュラムの活用案を[こちら](for-teachers.md)にまとめています。 --- ## ビデオウォークスルー -一部のレッスンは短い動画でご覧いただけます。これらはレッスン内にインラインであるほか、[Microsoft Developer YouTubeチャンネルのML for Beginnersプレイリスト](https://aka.ms/ml-beginners-videos)でも視聴可能です。下の画像をクリックしてください。 +一部のレッスンは短い動画で視聴可能です。レッスン内の埋め込みや、下の画像リンク先の[Microsoft Developer YouTubeチャンネルのML for Beginnersプレイリスト](https://aka.ms/ml-beginners-videos)でご覧いただけます。 -[![ML for beginners banner](../../../../translated_images/ja/ml-for-beginners-video-banner.63f694a100034bc6.webp)](https://aka.ms/ml-beginners-videos) +[![ML for beginners banner](../../translated_images/ja/ml-for-beginners-video-banner.63f694a100034bc6.webp)](https://aka.ms/ml-beginners-videos) --- @@ -97,81 +88,81 @@ MicrosoftのCloud Advocatesは、**機械学習**に関する12週間・全26レ [![Promo video](../../images/ml.gif)](https://youtu.be/Tj1XWrDSYJU) -**GIF作成** [Mohit Jaisal](https://linkedin.com/in/mohitjaisal) +**GIF提供** [Mohit Jaisal](https://linkedin.com/in/mohitjaisal) -> 🎥 プロジェクトや開発メンバーについての動画は上の画像をクリック！ +> 🎥 上の画像をクリックすると、プロジェクトと開発者についてのビデオが見られます！ --- ## 教育方針 -このカリキュラムは「実践的なプロジェクトベース」と「頻繁なクイズ」を柱としています。また、統一感を持たせるため共通の「テーマ」も設定しています。 +このカリキュラム作成にあたり、二つの教育上の柱を選びました：ハンズオンの**プロジェクトベース**であること、そして**頻繁なクイズ**を組み込むことです。さらに一貫性を持たせるために共通の**テーマ**を設定しました。 -プロジェクトと連動した内容により、学習への没入感が高まり、概念の定着が進みます。クラス前の低リスクなクイズは学生の学習意欲を高め、クラス後のもう一つのクイズは理解の深化を助けます。全体として柔軟かつ楽しく取り組めるよう設計されており、12週間サイクルの終わりにはより複雑な課題も含まれます。付録として実社会でのML応用例もあり、追加の課題や議論の素材として利用可能です。 +コンテンツがプロジェクトに沿うことで、学習者の関与が高まり、概念の保持が促進されます。また、授業前の軽いクイズが学習意欲を高め、授業後のクイズで記憶の定着を図ります。このカリキュラムは柔軟で楽しく、全体または一部だけでも学べます。プロジェクトは最初は簡単で、12週間の終盤にはより複雑になります。さらに、実社会における機械学習の応用についての後書きも含まれ、追加の学習や議論の材料として活用可能です。 -> [行動規範](CODE_OF_CONDUCT.md)、[貢献ガイドライン](CONTRIBUTING.md)、[翻訳ガイド](TRANSLATIONS.md)、[トラブルシューティング](TROUBLESHOOTING.md)もご覧ください。建設的なフィードバックを歓迎します！ +> [行動規範](CODE_OF_CONDUCT.md)、[貢献ガイド](CONTRIBUTING.md)、[翻訳ガイド](TRANSLATIONS.md)、[トラブルシューティング](TROUBLESHOOTING.md)をご覧ください。建設的なフィードバックを歓迎します！ -## 各レッスンに含まれるもの +## 各レッスンには以下を含みます -- オプションのスケッチノート -- オプションの補足動画 +- 任意のスケッチノート +- 任意の補足ビデオ - ビデオウォークスルー（一部のレッスンのみ） -- [事前講義ウォームアップクイズ](https://ff-quizzes.netlify.app/en/ml/) -- 書面によるレッスン -- プロジェクトベースレッスンでは、プロジェクト構築のステップバイステップガイド -- 知識チェック +- [事前講義用ウォームアップクイズ](https://ff-quizzes.netlify.app/en/ml/) +- 書かれたレッスン内容 +- プロジェクトベースのレッスンでは、プロジェクトを構築するステップバイステップのガイド +- 知識確認 - チャレンジ - 補足読書 - 課題 -- [事後講義クイズ](https://ff-quizzes.netlify.app/en/ml/) +- [事後講義用クイズ](https://ff-quizzes.netlify.app/en/ml/) -> **言語についての注記**：このレッスンは主にPythonで書かれていますが、多くはRでも提供されています。Rレッスンを完了するには、`/solution` フォルダ内のRレッスンを探してください。これらは.rmd拡張子を持ち、**R Markdown**ファイルを表しています。R Markdownは、`コードチャンク`（Rや他の言語）と、出力形式（PDFなど）を定義する`YAMLヘッダー`をMarkdownドキュメント内に組み込んだものです。これにより、コード、出力、考えをMarkdownで記述しつつ統合できる、データサイエンス向けの優れた著述フレームワークとなっています。また、R MarkdownドキュメントはPDF、HTML、Wordなどの形式にレンダリング可能です。 -> **クイズについての注意**: すべてのクイズは[Quiz Appフォルダー](../../quiz-app)に収められており、3問ずつ全52クイズがあります。レッスン内からリンクされていますが、quiz appはローカルで実行可能です。ローカルホスティングまたはAzureへのデプロイ方法は`quiz-app`フォルダー内の指示に従ってください。 +> **言語についての注意**：これらのレッスンは主にPythonで書かれていますが、多くはRでも提供しています。Rレッスンを行うには、`/solution`フォルダでRのレッスンを探してください。これには`.rmd`拡張子があり、これは**R Markdown**ファイルで、`コードチャンク`（Rや他の言語）と`YAMLヘッダー`（PDFなどの出力形式設定を指示）を組み合わせているMarkdown形式の文書です。そのため、コード、その出力、考えをMarkdownで一体的に書けるデータサイエンス向けの優れた執筆フレームワークです。R Markdown文書はPDFやHTML、Wordなどの形式にレンダリング可能です。 +> **クイズについての注記**: すべてのクイズは[Quiz Appフォルダー](../../quiz-app)に収められており、合計52個のクイズがあり、それぞれ3つの質問からなっています。レッスン内からリンクされていますが、クイズアプリはローカルで実行可能です。`quiz-app`フォルダー内の指示に従い、ローカルホストまたはAzureにデプロイしてください。 -| レッスン番号 | トピック | レッスングループ | 学習目標 | リンクされたレッスン | 著者 | +| レッスン番号 | トピック | レッスングループ | 学習目標 | リンクされたレッスン | 著者 | | :-----------: | :------------------------------------------------------------: | :-------------------------------------------------: | ------------------------------------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------: | -| 01 | 機械学習の紹介 | [Introduction](1-Introduction/README.md) | 機械学習の基本概念を学ぶ | [レッスン](1-Introduction/1-intro-to-ML/README.md) | Muhammad | -| 02 | 機械学習の歴史 | [Introduction](1-Introduction/README.md) | この分野の歴史を学ぶ | [レッスン](1-Introduction/2-history-of-ML/README.md) | Jen and Amy | -| 03 | 公平性と機械学習 | [Introduction](1-Introduction/README.md) | MLモデル構築と応用にあたり学生が考慮すべき重要な公平性に関する哲学的課題は何か？ | [レッスン](1-Introduction/3-fairness/README.md) | Tomomi | -| 04 | 機械学習の技術 | [Introduction](1-Introduction/README.md) | ML研究者がMLモデル構築に使う技術は何か？ | [レッスン](1-Introduction/4-techniques-of-ML/README.md) | Chris and Jen | -| 05 | 回帰の紹介 | [Regression](2-Regression/README.md) | PythonとScikit-learnで回帰モデルを始める | [Python](2-Regression/1-Tools/README.md) • [R](../../2-Regression/1-Tools/solution/R/lesson_1.html) | Jen • Eric Wanjau | -| 06 | 北米のカボチャ価格 🎃 | [Regression](2-Regression/README.md) | MLのためにデータを可視化しクリーニングする | [Python](2-Regression/2-Data/README.md) • [R](../../2-Regression/2-Data/solution/R/lesson_2.html) | Jen • Eric Wanjau | -| 07 | 北米のカボチャ価格 🎃 | [Regression](2-Regression/README.md) | 線形および多項式回帰モデルを構築する | [Python](2-Regression/3-Linear/README.md) • [R](../../2-Regression/3-Linear/solution/R/lesson_3.html) | Jen and Dmitry • Eric Wanjau | -| 08 | 北米のカボチャ価格 🎃 | [Regression](2-Regression/README.md) | ロジスティック回帰モデルを構築する | [Python](2-Regression/4-Logistic/README.md) • [R](../../2-Regression/4-Logistic/solution/R/lesson_4.html) | Jen • Eric Wanjau | -| 09 | Webアプリ 🔌 | [Web App](3-Web-App/README.md) | 学習済みモデルを使用するWebアプリを構築する | [Python](3-Web-App/1-Web-App/README.md) | Jen | -| 10 | 分類入門 | [Classification](4-Classification/README.md) | データをクリーニング・準備・可視化する；分類入門 | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | Jen and Cassie • Eric Wanjau | -| 11 | 美味しいアジアとインドの料理 🍜 | [Classification](4-Classification/README.md) | 分類器の紹介 | [Python](4-Classification/2-Classifiers-1/README.md) • [R](../../4-Classification/2-Classifiers-1/solution/R/lesson_11.html) | Jen and Cassie • Eric Wanjau | -| 12 | 美味しいアジアとインドの料理 🍜 | [Classification](4-Classification/README.md) | より多くの分類器 | [Python](4-Classification/3-Classifiers-2/README.md) • [R](../../4-Classification/3-Classifiers-2/solution/R/lesson_12.html) | Jen and Cassie • Eric Wanjau | -| 13 | 美味しいアジアとインドの料理 🍜 | [Classification](4-Classification/README.md) | モデルを使ったレコメンダーWebアプリを構築する | [Python](4-Classification/4-Applied/README.md) | Jen | -| 14 | クラスタリング入門 | [Clustering](5-Clustering/README.md) | データのクリーニング・準備・可視化；クラスタリング入門 | [Python](5-Clustering/1-Visualize/README.md) • [R](../../5-Clustering/1-Visualize/solution/R/lesson_14.html) | Jen • Eric Wanjau | -| 15 | ナイジェリアの音楽の趣味 🎧 | [Clustering](5-Clustering/README.md) | K-Meansクラスタリング手法を探求 | [Python](5-Clustering/2-K-Means/README.md) • [R](../../5-Clustering/2-K-Means/solution/R/lesson_15.html) | Jen • Eric Wanjau | -| 16 | 自然言語処理入門 ☕️ | [Natural language processing](6-NLP/README.md) | シンプルなボットを作ってNLPの基礎を学ぶ | [Python](6-NLP/1-Introduction-to-NLP/README.md) | Stephen | -| 17 | 一般的なNLPタスク ☕️ | [Natural language processing](6-NLP/README.md) | 言語構造を扱う際に必要な一般的なタスクを理解してNLP知識を深める | [Python](6-NLP/2-Tasks/README.md) | Stephen | -| 18 | 翻訳と感情分析 ♥️ | [Natural language processing](6-NLP/README.md) | ジェーン・オースティンの作品による翻訳と感情分析 | [Python](6-NLP/3-Translation-Sentiment/README.md) | Stephen | -| 19 | ヨーロッパのロマンチックなホテル ♥️ | [Natural language processing](6-NLP/README.md) | ホテルレビューによる感情分析 1 | [Python](6-NLP/4-Hotel-Reviews-1/README.md) | Stephen | -| 20 | ヨーロッパのロマンチックなホテル ♥️ | [Natural language processing](6-NLP/README.md) | ホテルレビューによる感情分析 2 | [Python](6-NLP/5-Hotel-Reviews-2/README.md) | Stephen | -| 21 | 時系列予測入門 | [Time series](7-TimeSeries/README.md) | 時系列予測入門 | [Python](7-TimeSeries/1-Introduction/README.md) | Francesca | -| 22 | ⚡️ 世界の電力使用量 ⚡️ - ARIMAによる時系列予測 | [Time series](7-TimeSeries/README.md) | ARIMAによる時系列予測 | [Python](7-TimeSeries/2-ARIMA/README.md) | Francesca | -| 23 | ⚡️ 世界の電力使用量 ⚡️ - SVRによる時系列予測 | [Time series](7-TimeSeries/README.md) | サポートベクター回帰による時系列予測 | [Python](7-TimeSeries/3-SVR/README.md) | Anirban | -| 24 | 強化学習入門 | [Reinforcement learning](8-Reinforcement/README.md) | Qラーニングを使った強化学習入門 | [Python](8-Reinforcement/1-QLearning/README.md) | Dmitry | -| 25 | ピーターがオオカミを避けるのを助けよう！ 🐺 | [Reinforcement learning](8-Reinforcement/README.md) | Gymによる強化学習 | [Python](8-Reinforcement/2-Gym/README.md) | Dmitry | -| ポストスクリプト | 現実世界のMLシナリオと応用 | [ML in the Wild](9-Real-World/README.md) | 古典的MLの興味深く示唆的な現実世界応用 | [レッスン](9-Real-World/1-Applications/README.md) | チーム | -| ポストスクリプト | RAIダッシュボードを用いたMLモデルデバッグ | [ML in the Wild](9-Real-World/README.md) | Responsible AIダッシュボードコンポーネントを活用した機械学習におけるモデルデバッグ | [レッスン](9-Real-World/2-Debugging-ML-Models/README.md) | Ruth Yakubu | - -> [このコースの追加リソースはすべてMicrosoft Learnコレクションで見つけられます](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) +| 01 | 機械学習の紹介 | [イントロダクション](1-Introduction/README.md) | 機械学習の基本的な概念を学ぶ | [レッスン](1-Introduction/1-intro-to-ML/README.md) | Muhammad | +| 02 | 機械学習の歴史 | [イントロダクション](1-Introduction/README.md) | この分野の基礎となる歴史を学ぶ | [レッスン](1-Introduction/2-history-of-ML/README.md) | Jen and Amy | +| 03 | 公平性と機械学習 | [イントロダクション](1-Introduction/README.md) | MLモデルを構築・適用する際に学生が考慮すべき重要な公平性に関する哲学的課題とは何か？ | [レッスン](1-Introduction/3-fairness/README.md) | Tomomi | +| 04 | 機械学習の技法 | [イントロダクション](1-Introduction/README.md) | ML研究者がMLモデルを構築するために使用する技法とは？ | [レッスン](1-Introduction/4-techniques-of-ML/README.md) | Chris and Jen | +| 05 | 回帰の紹介 | [回帰](2-Regression/README.md) | PythonとScikit-learnを使った回帰モデルの入門 | [Python](2-Regression/1-Tools/README.md) • [R](../../2-Regression/1-Tools/solution/R/lesson_1.html) | Jen • Eric Wanjau | +| 06 | 北米のパンプキン価格 🎃 | [回帰](2-Regression/README.md) | MLに向けてデータを可視化・クリーニングする | [Python](2-Regression/2-Data/README.md) • [R](../../2-Regression/2-Data/solution/R/lesson_2.html) | Jen • Eric Wanjau | +| 07 | 北米のパンプキン価格 🎃 | [回帰](2-Regression/README.md) | 線形回帰モデルと多項式回帰モデルの構築 | [Python](2-Regression/3-Linear/README.md) • [R](../../2-Regression/3-Linear/solution/R/lesson_3.html) | Jen and Dmitry • Eric Wanjau | +| 08 | 北米のパンプキン価格 🎃 | [回帰](2-Regression/README.md) | ロジスティック回帰モデルの構築 | [Python](2-Regression/4-Logistic/README.md) • [R](../../2-Regression/4-Logistic/solution/R/lesson_4.html) | Jen • Eric Wanjau | +| 09 | ウェブアプリ 🔌 | [Web App](3-Web-App/README.md) | 学習済みモデルを使うためのウェブアプリの構築 | [Python](3-Web-App/1-Web-App/README.md) | Jen | +| 10 | 分類の紹介 | [分類](4-Classification/README.md) | データをクリーニングし準備、可視化する；分類入門 | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | Jen and Cassie • Eric Wanjau | +| 11 | 美味しいアジアとインドの料理 🍜 | [分類](4-Classification/README.md) | 分類器の紹介 | [Python](4-Classification/2-Classifiers-1/README.md) • [R](../../4-Classification/2-Classifiers-1/solution/R/lesson_11.html) | Jen and Cassie • Eric Wanjau | +| 12 | 美味しいアジアとインドの料理 🍜 | [分類](4-Classification/README.md) | さらなる分類器 | [Python](4-Classification/3-Classifiers-2/README.md) • [R](../../4-Classification/3-Classifiers-2/solution/R/lesson_12.html) | Jen and Cassie • Eric Wanjau | +| 13 | 美味しいアジアとインドの料理 🍜 | [分類](4-Classification/README.md) | モデルを用いて推薦ウェブアプリを構築 | [Python](4-Classification/4-Applied/README.md) | Jen | +| 14 | クラスタリングの紹介 | [クラスタリング](5-Clustering/README.md) | データのクリーニング、準備、可視化；クラスタリング入門 | [Python](5-Clustering/1-Visualize/README.md) • [R](../../5-Clustering/1-Visualize/solution/R/lesson_14.html) | Jen • Eric Wanjau | +| 15 | ナイジェリアの音楽の趣味を探る 🎧 | [クラスタリング](5-Clustering/README.md) | K-平均クラスタリング手法を探求 | [Python](5-Clustering/2-K-Means/README.md) • [R](../../5-Clustering/2-K-Means/solution/R/lesson_15.html) | Jen • Eric Wanjau | +| 16 | 自然言語処理の紹介 ☕️ | [自然言語処理](6-NLP/README.md) | シンプルなボットを作ることでNLPの基礎を学ぶ | [Python](6-NLP/1-Introduction-to-NLP/README.md) | Stephen | +| 17 | よくあるNLPタスク ☕️ | [自然言語処理](6-NLP/README.md) | 言語構造を扱う際に必要な一般的なタスクを理解してNLPの知識を深める | [Python](6-NLP/2-Tasks/README.md) | Stephen | +| 18 | 翻訳と感情分析 ♥️ | [自然言語処理](6-NLP/README.md) | ジェーン・オースティンのテキストによる翻訳と感情分析 | [Python](6-NLP/3-Translation-Sentiment/README.md) | Stephen | +| 19 | ヨーロッパのロマンチックホテル ♥️ | [自然言語処理](6-NLP/README.md) | ホテルレビューを用いた感情分析 1 | [Python](6-NLP/4-Hotel-Reviews-1/README.md) | Stephen | +| 20 | ヨーロッパのロマンチックホテル ♥️ | [自然言語処理](6-NLP/README.md) | ホテルレビューを用いた感情分析 2 | [Python](6-NLP/5-Hotel-Reviews-2/README.md) | Stephen | +| 21 | 時系列予測の紹介 | [時系列](7-TimeSeries/README.md) | 時系列予測の入門 | [Python](7-TimeSeries/1-Introduction/README.md) | Francesca | +| 22 | ⚡️ 世界の電力使用量 ⚡️ - ARIMAによる時系列予測 | [時系列](7-TimeSeries/README.md) | ARIMAを用いた時系列予測 | [Python](7-TimeSeries/2-ARIMA/README.md) | Francesca | +| 23 | ⚡️ 世界の電力使用量 ⚡️ - SVRによる時系列予測 | [時系列](7-TimeSeries/README.md) | サポートベクター回帰を用いた時系列予測 | [Python](7-TimeSeries/3-SVR/README.md) | Anirban | +| 24 | 強化学習の紹介 | [強化学習](8-Reinforcement/README.md) | Q-ラーニングによる強化学習の紹介 | [Python](8-Reinforcement/1-QLearning/README.md) | Dmitry | +| 25 | ピーターにオオカミを避ける手助け！ 🐺 | [強化学習](8-Reinforcement/README.md) | 強化学習Gym | [Python](8-Reinforcement/2-Gym/README.md) | Dmitry | +| 追記 | 実世界のMLシナリオと応用 | [実世界のML](9-Real-World/README.md) | 古典的MLの興味深く示唆に富んだ実世界での応用例 | [レッスン](9-Real-World/1-Applications/README.md) | チーム | +| 追記 | RAIダッシュボードを用いたMLモデルのデバッグ | [実世界のML](9-Real-World/README.md) | Responsible AIダッシュボードコンポーネントを使った機械学習モデルのデバッグ | [レッスン](9-Real-World/2-Debugging-ML-Models/README.md) | Ruth Yakubu | + +> [このコースのすべての追加リソースはこちらのMicrosoft Learnコレクションでご覧いただけます](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) ## オフラインアクセス -[Docsify](https://docsify.js.org/#/)を使って、このドキュメントをオフラインで利用できます。このリポジトリをフォークし、ローカルマシンに[Docsifyをインストール](https://docsify.js.org/#/quickstart)してから、このリポジトリのルートフォルダーで `docsify serve` を実行してください。ウェブサイトはローカルホストのポート3000で提供されます：`localhost:3000`。 +[Docsify](https://docsify.js.org/#/)を使ってオフラインでこのドキュメントを実行できます。このリポジトリをフォークし、ローカルマシンに[Docsifyをインストール](https://docsify.js.org/#/quickstart)してから、このリポジトリのルートフォルダで`docsify serve`と入力してください。ウェブサイトはローカルホストのポート3000（`localhost:3000`）で提供されます。 ## PDF -カリキュラムのpdf（リンク付き）はこちらにあります: [here](https://microsoft.github.io/ML-For-Beginners/pdf/readme.pdf)。 +リンク付きのカリキュラムPDFは[こちら](https://microsoft.github.io/ML-For-Beginners/pdf/readme.pdf)でご覧いただけます。 ## 🎒 その他のコース -私たちのチームは他のコースも制作しています！ぜひチェックしてください： +私たちのチームは他にもコースを制作しています。ぜひチェックしてください： ### LangChain @@ -189,37 +180,37 @@ MicrosoftのCloud Advocatesは、**機械学習**に関する12週間・全26レ --- ### Generative AI Series -[![初心者向け生成AI](https://img.shields.io/badge/Generative%20AI%20for%20Beginners-8B5CF6?style=for-the-badge&labelColor=E5E7EB&color=8B5CF6)](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst) -[![生成AI（.NET）](https://img.shields.io/badge/Generative%20AI%20(.NET)-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst) -[![生成AI（Java）](https://img.shields.io/badge/Generative%20AI%20(Java)-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst) -[![生成AI（JavaScript）](https://img.shields.io/badge/Generative%20AI%20(JavaScript)-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst) +[![Generative AI for Beginners](https://img.shields.io/badge/Generative%20AI%20for%20Beginners-8B5CF6?style=for-the-badge&labelColor=E5E7EB&color=8B5CF6)](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst) +[![Generative AI (.NET)](https://img.shields.io/badge/Generative%20AI%20(.NET)-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst) +[![Generative AI (Java)](https://img.shields.io/badge/Generative%20AI%20(Java)-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst) +[![Generative AI (JavaScript)](https://img.shields.io/badge/Generative%20AI%20(JavaScript)-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst) --- - + ### コアラーニング -[![初心者向け機械学習](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) -[![初心者向けデータサイエンス](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) -[![初心者向けAI](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) -[![初心者向けサイバーセキュリティ](https://img.shields.io/badge/Cybersecurity%20for%20Beginners-F97316?style=for-the-badge&labelColor=E5E7EB&color=F97316)](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung) -[![初心者向けウェブ開発](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst) -[![初心者向けIoT](https://img.shields.io/badge/IoT%20for%20Beginners-14B8A6?style=for-the-badge&labelColor=E5E7EB&color=14B8A6)](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst) -[![初心者向けXR開発](https://img.shields.io/badge/XR%20Development%20for%20Beginners-38BDF8?style=for-the-badge&labelColor=E5E7EB&color=38BDF8)](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst) +[![ML for Beginners](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) +[![Data Science for Beginners](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) +[![AI for Beginners](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) +[![Cybersecurity for Beginners](https://img.shields.io/badge/Cybersecurity%20for%20Beginners-F97316?style=for-the-badge&labelColor=E5E7EB&color=F97316)](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung) +[![Web Dev for Beginners](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst) +[![IoT for Beginners](https://img.shields.io/badge/IoT%20for%20Beginners-14B8A6?style=for-the-badge&labelColor=E5E7EB&color=14B8A6)](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst) +[![XR Development for Beginners](https://img.shields.io/badge/XR%20Development%20for%20Beginners-38BDF8?style=for-the-badge&labelColor=E5E7EB&color=38BDF8)](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst) --- - + ### コパイロットシリーズ -[![AIペアプログラミング用コパイロット](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) -[![C#/.NET用コパイロット](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst) -[![コパイロットアドベンチャー](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) +[![Copilot for AI Paired Programming](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) +[![Copilot for C#/.NET](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst) +[![Copilot Adventure](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) -## ヘルプの取得 +## ヘルプを得る -AIアプリの構築で行き詰まったり質問がある場合は、MCPの学習者や経験豊富な開発者たちとディスカッションに参加しましょう。質問が歓迎され、知識が自由に共有されるサポートコミュニティです。 +AIアプリケーションの構築で行き詰まったり質問がある場合は、学習者や経験豊富な開発者と一緒にMCPのディスカッションに参加しましょう。質問が歓迎され知識が自由に共有されるサポートコミュニティです。 [![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -製品のフィードバックや構築中のエラーについては以下をご覧ください： +製品のフィードバックや、構築中にエラーが発生した場合は、以下を訪問してください： [![Microsoft Foundry Developer Forum](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum) @@ -227,5 +218,5 @@ AIアプリの構築で行き詰まったり質問がある場合は、MCPの学 **免責事項**： -本ドキュメントはAI翻訳サービス「Co-op Translator」（https://github.com/Azure/co-op-translator）を使用して翻訳されました。正確性には努めておりますが、自動翻訳には誤りや不正確な箇所が含まれる可能性があることをご承知おきください。原文の言語によるオリジナルの文書が正式な情報源とみなされます。重要な情報については、専門の翻訳者による人力翻訳を推奨いたします。本翻訳の利用により生じたいかなる誤解や誤訳についても責任を負いかねます。 +本書類はAI翻訳サービス「Co-op Translator」（https://github.com/Azure/co-op-translator）を使用して翻訳されました。正確性を期しておりますが、自動翻訳には誤りや不正確な部分が含まれる可能性があることをご承知おきください。原文はその言語における正式な文書とみなされます。重要な情報については、専門の人間による翻訳を推奨いたします。本翻訳の利用により生じた誤解や誤訳について、当方は一切の責任を負いかねます。 \ No newline at end of file diff --git a/translations/ja/SECURITY.md b/translations/ja/SECURITY.md index b6ddd569f..ad8df98eb 100644 --- a/translations/ja/SECURITY.md +++ b/translations/ja/SECURITY.md @@ -1,12 +1,3 @@ - ## セキュリティ Microsoftは、ソフトウェア製品やサービスのセキュリティを非常に重要視しています。これには、[Microsoft](https://github.com/Microsoft)、[Azure](https://github.com/Azure)、[DotNet](https://github.com/dotnet)、[AspNet](https://github.com/aspnet)、[Xamarin](https://github.com/xamarin)、および[弊社のGitHub組織](https://opensource.microsoft.com/)で管理されているすべてのソースコードリポジトリが含まれます。 diff --git a/translations/ja/SUPPORT.md b/translations/ja/SUPPORT.md index 1c0271347..9c68bfe04 100644 --- a/translations/ja/SUPPORT.md +++ b/translations/ja/SUPPORT.md @@ -1,12 +1,3 @@ - # サポート ## 問題の報告方法とヘルプの取得方法 diff --git a/translations/ja/TROUBLESHOOTING.md b/translations/ja/TROUBLESHOOTING.md index eb19ed1ab..aca3fc616 100644 --- a/translations/ja/TROUBLESHOOTING.md +++ b/translations/ja/TROUBLESHOOTING.md @@ -1,12 +1,3 @@ - # トラブルシューティングガイド このガイドは、Machine Learning for Beginners カリキュラムでよくある問題を解決するための手助けをします。ここで解決策が見つからない場合は、[Discord Discussions](https://aka.ms/foundry/discord) を確認するか、[問題を報告](https://github.com/microsoft/ML-For-Beginners/issues)してください。 diff --git a/translations/ja/docs/_sidebar.md b/translations/ja/docs/_sidebar.md index b7b117ec3..b22f47d3a 100644 --- a/translations/ja/docs/_sidebar.md +++ b/translations/ja/docs/_sidebar.md @@ -1,12 +1,3 @@ - - はじめに - [機械学習の紹介](../1-Introduction/1-intro-to-ML/README.md) - [機械学習の歴史](../1-Introduction/2-history-of-ML/README.md) diff --git a/translations/ja/for-teachers.md b/translations/ja/for-teachers.md index 817d0a9d5..c62a14384 100644 --- a/translations/ja/for-teachers.md +++ b/translations/ja/for-teachers.md @@ -1,12 +1,3 @@ - ## 教育者向け このカリキュラムを教室で使用してみませんか？ぜひご活用ください！ diff --git a/translations/ja/quiz-app/README.md b/translations/ja/quiz-app/README.md index 8b03f2de9..927185e25 100644 --- a/translations/ja/quiz-app/README.md +++ b/translations/ja/quiz-app/README.md @@ -1,12 +1,3 @@ - # クイズ これらのクイズは、https://aka.ms/ml-beginners にあるMLカリキュラムの講義前後のクイズです。 diff --git a/translations/ja/sketchnotes/LICENSE.md b/translations/ja/sketchnotes/LICENSE.md index 48ee8920d..45ed222cc 100644 --- a/translations/ja/sketchnotes/LICENSE.md +++ b/translations/ja/sketchnotes/LICENSE.md @@ -1,12 +1,3 @@ - 著作権表示-継承 4.0 国際 ======================================================================= diff --git a/translations/ja/sketchnotes/README.md b/translations/ja/sketchnotes/README.md index 03f5ad424..cb88659ab 100644 --- a/translations/ja/sketchnotes/README.md +++ b/translations/ja/sketchnotes/README.md @@ -1,12 +1,3 @@ - すべてのカリキュラムのスケッチノートはここからダウンロードできます。 🖨 高解像度で印刷する場合、TIFFバージョンが[このリポジトリ](https://github.com/girliemac/a-picture-is-worth-a-1000-words/tree/main/ml/tiff)で利用可能です。 diff --git a/translations/ko/.co-op-translator.json b/translations/ko/.co-op-translator.json new file mode 100644 index 000000000..1fdde9106 --- /dev/null +++ b/translations/ko/.co-op-translator.json @@ -0,0 +1,596 @@ +{ + "1-Introduction/1-intro-to-ML/README.md": { + "original_hash": "69389392fa6346e0dfa30f664b7b6fec", + "translation_date": "2025-09-05T10:49:01+00:00", + "source_file": "1-Introduction/1-intro-to-ML/README.md", + "language_code": "ko" + }, + "1-Introduction/1-intro-to-ML/assignment.md": { + "original_hash": "4c4698044bb8af52cfb6388a4ee0e53b", + "translation_date": "2025-09-03T23:38:35+00:00", + "source_file": "1-Introduction/1-intro-to-ML/assignment.md", + "language_code": "ko" + }, + "1-Introduction/2-history-of-ML/README.md": { + "original_hash": "6a05fec147e734c3e6bfa54505648e2b", + "translation_date": "2025-09-05T10:49:35+00:00", + "source_file": "1-Introduction/2-history-of-ML/README.md", + "language_code": "ko" + }, + "1-Introduction/2-history-of-ML/assignment.md": { + "original_hash": "eb6e4d5afd1b21a57d2b9e6d0aac3969", + "translation_date": "2025-09-03T23:42:32+00:00", + "source_file": "1-Introduction/2-history-of-ML/assignment.md", + "language_code": "ko" + }, + "1-Introduction/3-fairness/README.md": { + "original_hash": "9a6b702d1437c0467e3c5c28d763dac2", + "translation_date": "2025-09-05T10:47:40+00:00", + "source_file": "1-Introduction/3-fairness/README.md", + "language_code": "ko" + }, + "1-Introduction/3-fairness/assignment.md": { + "original_hash": "dbda60e7b1fe5f18974e7858eff0004e", + "translation_date": "2025-09-03T23:31:20+00:00", + "source_file": "1-Introduction/3-fairness/assignment.md", + "language_code": "ko" + }, + "1-Introduction/4-techniques-of-ML/README.md": { + "original_hash": "9d91f3af3758fdd4569fb410575995ef", + "translation_date": "2025-09-05T10:48:28+00:00", + "source_file": "1-Introduction/4-techniques-of-ML/README.md", + "language_code": "ko" + }, + "1-Introduction/4-techniques-of-ML/assignment.md": { + "original_hash": "70d65aeddc06170bc1aed5b27805f930", + "translation_date": "2025-09-03T23:35:16+00:00", + "source_file": "1-Introduction/4-techniques-of-ML/assignment.md", + "language_code": "ko" + }, + "1-Introduction/README.md": { + "original_hash": "cf8ecc83f28e5b98051d2179eca08e08", + "translation_date": "2025-09-03T23:26:03+00:00", + "source_file": "1-Introduction/README.md", + "language_code": "ko" + }, + "2-Regression/1-Tools/README.md": { + "original_hash": "fa81d226c71d5af7a2cade31c1c92b88", + "translation_date": "2025-09-05T10:41:04+00:00", + "source_file": "2-Regression/1-Tools/README.md", + "language_code": "ko" + }, + "2-Regression/1-Tools/assignment.md": { + "original_hash": "74a5cf83e4ebc302afbcbc4f418afd0a", + "translation_date": "2025-09-03T22:36:19+00:00", + "source_file": "2-Regression/1-Tools/assignment.md", + "language_code": "ko" + }, + "2-Regression/1-Tools/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T22:36:48+00:00", + "source_file": "2-Regression/1-Tools/solution/Julia/README.md", + "language_code": "ko" + }, + "2-Regression/2-Data/README.md": { + "original_hash": "7c077988328ebfe33b24d07945f16eca", + "translation_date": "2025-09-05T10:41:52+00:00", + "source_file": "2-Regression/2-Data/README.md", + "language_code": "ko" + }, + "2-Regression/2-Data/assignment.md": { + "original_hash": "4485a1ed4dd1b5647365e3d87456515d", + "translation_date": "2025-09-03T22:40:25+00:00", + "source_file": "2-Regression/2-Data/assignment.md", + "language_code": "ko" + }, + "2-Regression/2-Data/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T22:40:51+00:00", + "source_file": "2-Regression/2-Data/solution/Julia/README.md", + "language_code": "ko" + }, + "2-Regression/3-Linear/README.md": { + "original_hash": "40e64f004f3cb50aa1d8661672d3cd92", + "translation_date": "2025-09-05T10:37:57+00:00", + "source_file": "2-Regression/3-Linear/README.md", + "language_code": "ko" + }, + "2-Regression/3-Linear/assignment.md": { + "original_hash": "cc471fa89c293bc735dd3a9a0fb79b1b", + "translation_date": "2025-09-03T22:22:10+00:00", + "source_file": "2-Regression/3-Linear/assignment.md", + "language_code": "ko" + }, + "2-Regression/3-Linear/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T22:22:37+00:00", + "source_file": "2-Regression/3-Linear/solution/Julia/README.md", + "language_code": "ko" + }, + "2-Regression/4-Logistic/README.md": { + "original_hash": "abf86d845c84330bce205a46b382ec88", + "translation_date": "2025-09-05T10:40:02+00:00", + "source_file": "2-Regression/4-Logistic/README.md", + "language_code": "ko" + }, + "2-Regression/4-Logistic/assignment.md": { + "original_hash": "8af40209a41494068c1f42b14c0b450d", + "translation_date": "2025-09-03T22:31:17+00:00", + "source_file": "2-Regression/4-Logistic/assignment.md", + "language_code": "ko" + }, + "2-Regression/4-Logistic/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T22:31:43+00:00", + "source_file": "2-Regression/4-Logistic/solution/Julia/README.md", + "language_code": "ko" + }, + "2-Regression/README.md": { + "original_hash": "508582278dbb8edd2a8a80ac96ef416c", + "translation_date": "2025-09-03T22:15:17+00:00", + "source_file": "2-Regression/README.md", + "language_code": "ko" + }, + "3-Web-App/1-Web-App/README.md": { + "original_hash": "e0b75f73e4a90d45181dc5581fe2ef5c", + "translation_date": "2025-09-05T10:50:13+00:00", + "source_file": "3-Web-App/1-Web-App/README.md", + "language_code": "ko" + }, + "3-Web-App/1-Web-App/assignment.md": { + "original_hash": "a8e8ae10be335cbc745b75ee552317ff", + "translation_date": "2025-09-03T23:47:17+00:00", + "source_file": "3-Web-App/1-Web-App/assignment.md", + "language_code": "ko" + }, + "3-Web-App/README.md": { + "original_hash": "9836ff53cfef716ddfd70e06c5f43436", + "translation_date": "2025-09-03T23:43:15+00:00", + "source_file": "3-Web-App/README.md", + "language_code": "ko" + }, + "4-Classification/1-Introduction/README.md": { + "original_hash": "aaf391d922bd6de5efba871d514c6d47", + "translation_date": "2025-09-05T10:52:28+00:00", + "source_file": "4-Classification/1-Introduction/README.md", + "language_code": "ko" + }, + "4-Classification/1-Introduction/assignment.md": { + "original_hash": "b2a01912beb24cfb0007f83594dba801", + "translation_date": "2025-09-04T00:04:05+00:00", + "source_file": "4-Classification/1-Introduction/assignment.md", + "language_code": "ko" + }, + "4-Classification/1-Introduction/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-04T00:04:36+00:00", + "source_file": "4-Classification/1-Introduction/solution/Julia/README.md", + "language_code": "ko" + }, + "4-Classification/2-Classifiers-1/README.md": { + "original_hash": "1a6e9e46b34a2e559fbbfc1f95397c7b", + "translation_date": "2025-09-05T10:50:49+00:00", + "source_file": "4-Classification/2-Classifiers-1/README.md", + "language_code": "ko" + }, + "4-Classification/2-Classifiers-1/assignment.md": { + "original_hash": "de6025f96841498b0577e9d1aee18d1f", + "translation_date": "2025-09-03T23:54:05+00:00", + "source_file": "4-Classification/2-Classifiers-1/assignment.md", + "language_code": "ko" + }, + "4-Classification/2-Classifiers-1/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T23:54:33+00:00", + "source_file": "4-Classification/2-Classifiers-1/solution/Julia/README.md", + "language_code": "ko" + }, + "4-Classification/3-Classifiers-2/README.md": { + "original_hash": "49047911108adc49d605cddfb455749c", + "translation_date": "2025-09-05T10:52:05+00:00", + "source_file": "4-Classification/3-Classifiers-2/README.md", + "language_code": "ko" + }, + "4-Classification/3-Classifiers-2/assignment.md": { + "original_hash": "58dfdaf79fb73f7d34b22bdbacf57329", + "translation_date": "2025-09-04T00:00:10+00:00", + "source_file": "4-Classification/3-Classifiers-2/assignment.md", + "language_code": "ko" + }, + "4-Classification/3-Classifiers-2/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-04T00:00:51+00:00", + "source_file": "4-Classification/3-Classifiers-2/solution/Julia/README.md", + "language_code": "ko" + }, + "4-Classification/4-Applied/README.md": { + "original_hash": "61bdec27ed2da8b098cd9065405d9bb0", + "translation_date": "2025-09-05T10:51:38+00:00", + "source_file": "4-Classification/4-Applied/README.md", + "language_code": "ko" + }, + "4-Classification/4-Applied/assignment.md": { + "original_hash": "799ed651e2af0a7cad17c6268db11578", + "translation_date": "2025-09-03T23:57:27+00:00", + "source_file": "4-Classification/4-Applied/assignment.md", + "language_code": "ko" + }, + "4-Classification/README.md": { + "original_hash": "74e809ffd1e613a1058bbc3e9600859e", + "translation_date": "2025-09-03T23:49:04+00:00", + "source_file": "4-Classification/README.md", + "language_code": "ko" + }, + "5-Clustering/1-Visualize/README.md": { + "original_hash": "730225ea274c9174fe688b21d421539d", + "translation_date": "2025-09-05T10:44:24+00:00", + "source_file": "5-Clustering/1-Visualize/README.md", + "language_code": "ko" + }, + "5-Clustering/1-Visualize/assignment.md": { + "original_hash": "589fa015a5e7d9e67bd629f7d47b53de", + "translation_date": "2025-09-03T23:09:14+00:00", + "source_file": "5-Clustering/1-Visualize/assignment.md", + "language_code": "ko" + }, + "5-Clustering/1-Visualize/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T23:09:46+00:00", + "source_file": "5-Clustering/1-Visualize/solution/Julia/README.md", + "language_code": "ko" + }, + "5-Clustering/2-K-Means/README.md": { + "original_hash": "7cdd17338d9bbd7e2171c2cd462eb081", + "translation_date": "2025-09-05T10:45:29+00:00", + "source_file": "5-Clustering/2-K-Means/README.md", + "language_code": "ko" + }, + "5-Clustering/2-K-Means/assignment.md": { + "original_hash": "b8e17eff34ad1680eba2a5d3cf9ffc41", + "translation_date": "2025-09-03T23:12:50+00:00", + "source_file": "5-Clustering/2-K-Means/assignment.md", + "language_code": "ko" + }, + "5-Clustering/2-K-Means/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T23:13:18+00:00", + "source_file": "5-Clustering/2-K-Means/solution/Julia/README.md", + "language_code": "ko" + }, + "5-Clustering/README.md": { + "original_hash": "b28a3a4911584062772c537b653ebbc7", + "translation_date": "2025-09-03T22:55:54+00:00", + "source_file": "5-Clustering/README.md", + "language_code": "ko" + }, + "6-NLP/1-Introduction-to-NLP/README.md": { + "original_hash": "1c2ec40cf55c98a028a359c27ef7e45a", + "translation_date": "2025-09-05T10:56:52+00:00", + "source_file": "6-NLP/1-Introduction-to-NLP/README.md", + "language_code": "ko" + }, + "6-NLP/1-Introduction-to-NLP/assignment.md": { + "original_hash": "1d7583e8046dacbb0c056d5ba0a71b16", + "translation_date": "2025-09-04T00:49:11+00:00", + "source_file": "6-NLP/1-Introduction-to-NLP/assignment.md", + "language_code": "ko" + }, + "6-NLP/2-Tasks/README.md": { + "original_hash": "5f3cb462e3122e1afe7ab0050ccf2bd3", + "translation_date": "2025-09-05T10:55:03+00:00", + "source_file": "6-NLP/2-Tasks/README.md", + "language_code": "ko" + }, + "6-NLP/2-Tasks/assignment.md": { + "original_hash": "2efc4c2aba5ed06c780c05539c492ae3", + "translation_date": "2025-09-04T00:37:20+00:00", + "source_file": "6-NLP/2-Tasks/assignment.md", + "language_code": "ko" + }, + "6-NLP/3-Translation-Sentiment/README.md": { + "original_hash": "be03c8182982b87ced155e4e9d1438e8", + "translation_date": "2025-09-05T10:57:30+00:00", + "source_file": "6-NLP/3-Translation-Sentiment/README.md", + "language_code": "ko" + }, + "6-NLP/3-Translation-Sentiment/assignment.md": { + "original_hash": "9d2a734deb904caff310d1a999c6bd7a", + "translation_date": "2025-09-04T00:53:57+00:00", + "source_file": "6-NLP/3-Translation-Sentiment/assignment.md", + "language_code": "ko" + }, + "6-NLP/3-Translation-Sentiment/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-04T00:54:46+00:00", + "source_file": "6-NLP/3-Translation-Sentiment/solution/Julia/README.md", + "language_code": "ko" + }, + "6-NLP/3-Translation-Sentiment/solution/R/README.md": { + "original_hash": "81db6ff2cf6e62fbe2340b094bb9509e", + "translation_date": "2025-09-04T00:54:28+00:00", + "source_file": "6-NLP/3-Translation-Sentiment/solution/R/README.md", + "language_code": "ko" + }, + "6-NLP/4-Hotel-Reviews-1/README.md": { + "original_hash": "8d32dadeda93c6fb5c43619854882ab1", + "translation_date": "2025-09-05T10:55:43+00:00", + "source_file": "6-NLP/4-Hotel-Reviews-1/README.md", + "language_code": "ko" + }, + "6-NLP/4-Hotel-Reviews-1/assignment.md": { + "original_hash": "bf39bceb833cd628f224941dca8041df", + "translation_date": "2025-09-04T00:44:28+00:00", + "source_file": "6-NLP/4-Hotel-Reviews-1/assignment.md", + "language_code": "ko" + }, + "6-NLP/4-Hotel-Reviews-1/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-04T00:45:11+00:00", + "source_file": "6-NLP/4-Hotel-Reviews-1/solution/Julia/README.md", + "language_code": "ko" + }, + "6-NLP/4-Hotel-Reviews-1/solution/R/README.md": { + "original_hash": "81db6ff2cf6e62fbe2340b094bb9509e", + "translation_date": "2025-09-04T00:44:54+00:00", + "source_file": "6-NLP/4-Hotel-Reviews-1/solution/R/README.md", + "language_code": "ko" + }, + "6-NLP/5-Hotel-Reviews-2/README.md": { + "original_hash": "2c742993fe95d5bcbb2846eda3d442a1", + "translation_date": "2025-09-05T10:58:14+00:00", + "source_file": "6-NLP/5-Hotel-Reviews-2/README.md", + "language_code": "ko" + }, + "6-NLP/5-Hotel-Reviews-2/assignment.md": { + "original_hash": "daf144daa552da6a7d442aff6f3e77d8", + "translation_date": "2025-09-04T00:59:49+00:00", + "source_file": "6-NLP/5-Hotel-Reviews-2/assignment.md", + "language_code": "ko" + }, + "6-NLP/5-Hotel-Reviews-2/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-04T01:00:36+00:00", + "source_file": "6-NLP/5-Hotel-Reviews-2/solution/Julia/README.md", + "language_code": "ko" + }, + "6-NLP/5-Hotel-Reviews-2/solution/R/README.md": { + "original_hash": "81db6ff2cf6e62fbe2340b094bb9509e", + "translation_date": "2025-09-04T01:00:18+00:00", + "source_file": "6-NLP/5-Hotel-Reviews-2/solution/R/README.md", + "language_code": "ko" + }, + "6-NLP/README.md": { + "original_hash": "1eb379dc2d0c9940b320732d16083778", + "translation_date": "2025-09-04T00:33:10+00:00", + "source_file": "6-NLP/README.md", + "language_code": "ko" + }, + "6-NLP/data/README.md": { + "original_hash": "ee0670655c89e4719319764afb113624", + "translation_date": "2025-09-04T00:45:32+00:00", + "source_file": "6-NLP/data/README.md", + "language_code": "ko" + }, + "7-TimeSeries/1-Introduction/README.md": { + "original_hash": "662b509c39eee205687726636d0a8455", + "translation_date": "2025-09-05T10:43:16+00:00", + "source_file": "7-TimeSeries/1-Introduction/README.md", + "language_code": "ko" + }, + "7-TimeSeries/1-Introduction/assignment.md": { + "original_hash": "d1781b0b92568ea1d119d0a198b576b4", + "translation_date": "2025-09-03T22:50:51+00:00", + "source_file": "7-TimeSeries/1-Introduction/assignment.md", + "language_code": "ko" + }, + "7-TimeSeries/1-Introduction/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T22:51:40+00:00", + "source_file": "7-TimeSeries/1-Introduction/solution/Julia/README.md", + "language_code": "ko" + }, + "7-TimeSeries/1-Introduction/solution/R/README.md": { + "original_hash": "81db6ff2cf6e62fbe2340b094bb9509e", + "translation_date": "2025-09-03T22:51:22+00:00", + "source_file": "7-TimeSeries/1-Introduction/solution/R/README.md", + "language_code": "ko" + }, + "7-TimeSeries/2-ARIMA/README.md": { + "original_hash": "917dbf890db71a322f306050cb284749", + "translation_date": "2025-09-05T10:42:27+00:00", + "source_file": "7-TimeSeries/2-ARIMA/README.md", + "language_code": "ko" + }, + "7-TimeSeries/2-ARIMA/assignment.md": { + "original_hash": "1c814013e10866dfd92cdb32caaae3ac", + "translation_date": "2025-09-03T22:46:26+00:00", + "source_file": "7-TimeSeries/2-ARIMA/assignment.md", + "language_code": "ko" + }, + "7-TimeSeries/2-ARIMA/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-03T22:47:11+00:00", + "source_file": "7-TimeSeries/2-ARIMA/solution/Julia/README.md", + "language_code": "ko" + }, + "7-TimeSeries/2-ARIMA/solution/R/README.md": { + "original_hash": "81db6ff2cf6e62fbe2340b094bb9509e", + "translation_date": "2025-09-03T22:46:53+00:00", + "source_file": "7-TimeSeries/2-ARIMA/solution/R/README.md", + "language_code": "ko" + }, + "7-TimeSeries/3-SVR/README.md": { + "original_hash": "482bccabe1df958496ea71a3667995cd", + "translation_date": "2025-09-05T10:43:53+00:00", + "source_file": "7-TimeSeries/3-SVR/README.md", + "language_code": "ko" + }, + "7-TimeSeries/3-SVR/assignment.md": { + "original_hash": "94aa2fc6154252ae30a3f3740299707a", + "translation_date": "2025-09-03T22:55:05+00:00", + "source_file": "7-TimeSeries/3-SVR/assignment.md", + "language_code": "ko" + }, + "7-TimeSeries/README.md": { + "original_hash": "61342603bad8acadbc6b2e4e3aab3f66", + "translation_date": "2025-09-03T22:41:21+00:00", + "source_file": "7-TimeSeries/README.md", + "language_code": "ko" + }, + "8-Reinforcement/1-QLearning/README.md": { + "original_hash": "911efd5e595089000cb3c16fce1beab8", + "translation_date": "2025-09-05T10:53:41+00:00", + "source_file": "8-Reinforcement/1-QLearning/README.md", + "language_code": "ko" + }, + "8-Reinforcement/1-QLearning/assignment.md": { + "original_hash": "68394b2102d3503882e5e914bd0ff5c1", + "translation_date": "2025-09-04T00:23:54+00:00", + "source_file": "8-Reinforcement/1-QLearning/assignment.md", + "language_code": "ko" + }, + "8-Reinforcement/1-QLearning/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-04T00:25:33+00:00", + "source_file": "8-Reinforcement/1-QLearning/solution/Julia/README.md", + "language_code": "ko" + }, + "8-Reinforcement/1-QLearning/solution/R/README.md": { + "original_hash": "81db6ff2cf6e62fbe2340b094bb9509e", + "translation_date": "2025-09-04T00:25:16+00:00", + "source_file": "8-Reinforcement/1-QLearning/solution/R/README.md", + "language_code": "ko" + }, + "8-Reinforcement/2-Gym/README.md": { + "original_hash": "107d5bb29da8a562e7ae72262d251a75", + "translation_date": "2025-09-05T10:54:20+00:00", + "source_file": "8-Reinforcement/2-Gym/README.md", + "language_code": "ko" + }, + "8-Reinforcement/2-Gym/assignment.md": { + "original_hash": "1f2b7441745eb52e25745423b247016b", + "translation_date": "2025-09-04T00:31:20+00:00", + "source_file": "8-Reinforcement/2-Gym/assignment.md", + "language_code": "ko" + }, + "8-Reinforcement/2-Gym/solution/Julia/README.md": { + "original_hash": "a39c15d63f3b2795ee2284a82b986b93", + "translation_date": "2025-09-04T00:32:38+00:00", + "source_file": "8-Reinforcement/2-Gym/solution/Julia/README.md", + "language_code": "ko" + }, + "8-Reinforcement/2-Gym/solution/R/README.md": { + "original_hash": "81db6ff2cf6e62fbe2340b094bb9509e", + "translation_date": "2025-09-04T00:32:21+00:00", + "source_file": "8-Reinforcement/2-Gym/solution/R/README.md", + "language_code": "ko" + }, + "8-Reinforcement/README.md": { + "original_hash": "20ca019012b1725de956681d036d8b18", + "translation_date": "2025-09-04T00:14:05+00:00", + "source_file": "8-Reinforcement/README.md", + "language_code": "ko" + }, + "9-Real-World/1-Applications/README.md": { + "original_hash": "83320d6b6994909e35d830cebf214039", + "translation_date": "2025-09-05T10:45:58+00:00", + "source_file": "9-Real-World/1-Applications/README.md", + "language_code": "ko" + }, + "9-Real-World/1-Applications/assignment.md": { + "original_hash": "fdebfcd0a3f12c9e2b436ded1aa79885", + "translation_date": "2025-09-03T23:19:33+00:00", + "source_file": "9-Real-World/1-Applications/assignment.md", + "language_code": "ko" + }, + "9-Real-World/2-Debugging-ML-Models/README.md": { + "original_hash": "df2b538e8fbb3e91cf0419ae2f858675", + "translation_date": "2025-09-05T10:46:42+00:00", + "source_file": "9-Real-World/2-Debugging-ML-Models/README.md", + "language_code": "ko" + }, + "9-Real-World/2-Debugging-ML-Models/assignment.md": { + "original_hash": "91c6a180ef08e20cc15acfd2d6d6e164", + "translation_date": "2025-09-03T23:25:23+00:00", + "source_file": "9-Real-World/2-Debugging-ML-Models/assignment.md", + "language_code": "ko" + }, + "9-Real-World/README.md": { + "original_hash": "5e069a0ac02a9606a69946c2b3c574a9", + "translation_date": "2025-09-03T23:14:42+00:00", + "source_file": "9-Real-World/README.md", + "language_code": "ko" + }, + "AGENTS.md": { + "original_hash": "93fdaa0fd38836e50c4793e2f2f25e8b", + "translation_date": "2025-10-03T11:02:30+00:00", + "source_file": "AGENTS.md", + "language_code": "ko" + }, + "CODE_OF_CONDUCT.md": { + "original_hash": "c06b12caf3c901eb3156e3dd5b0aea56", + "translation_date": "2025-09-03T22:14:33+00:00", + "source_file": "CODE_OF_CONDUCT.md", + "language_code": "ko" + }, + "CONTRIBUTING.md": { + "original_hash": "977ec5266dfd78ad1ce2bd8d46fccbda", + "translation_date": "2025-09-03T22:11:50+00:00", + "source_file": "CONTRIBUTING.md", + "language_code": "ko" + }, + "README.md": { + "original_hash": "da2ceed62f16a0820259556e3a873c95", + "translation_date": "2026-01-29T18:04:38+00:00", + "source_file": "README.md", + "language_code": "ko" + }, + "SECURITY.md": { + "original_hash": "5e1b8da31aae9cca3d53ad243fa3365a", + "translation_date": "2025-09-03T22:12:41+00:00", + "source_file": "SECURITY.md", + "language_code": "ko" + }, + "SUPPORT.md": { + "original_hash": "09623d7343ff1c26ff4f198c1b2d3176", + "translation_date": "2025-10-03T11:48:07+00:00", + "source_file": "SUPPORT.md", + "language_code": "ko" + }, + "TROUBLESHOOTING.md": { + "original_hash": "134d8759f0e2ab886e9aa4f62362c201", + "translation_date": "2025-10-03T12:40:34+00:00", + "source_file": "TROUBLESHOOTING.md", + "language_code": "ko" + }, + "docs/_sidebar.md": { + "original_hash": "68dd06c685f6ce840e0acfa313352e7c", + "translation_date": "2025-09-03T23:13:49+00:00", + "source_file": "docs/_sidebar.md", + "language_code": "ko" + }, + "for-teachers.md": { + "original_hash": "b37de02054fa6c0438ede6fabe1fdfb8", + "translation_date": "2025-09-03T22:13:49+00:00", + "source_file": "for-teachers.md", + "language_code": "ko" + }, + "quiz-app/README.md": { + "original_hash": "6d130dffca5db70d7e615f926cb1ad4c", + "translation_date": "2025-09-03T23:48:02+00:00", + "source_file": "quiz-app/README.md", + "language_code": "ko" + }, + "sketchnotes/LICENSE.md": { + "original_hash": "fba3b94d88bfb9b81369b869a1e9a20f", + "translation_date": "2025-09-04T00:09:13+00:00", + "source_file": "sketchnotes/LICENSE.md", + "language_code": "ko" + }, + "sketchnotes/README.md": { + "original_hash": "a88d5918c1b9da69a40d917a0840c497", + "translation_date": "2025-09-04T00:04:58+00:00", + "source_file": "sketchnotes/README.md", + "language_code": "ko" + } +} \ No newline at end of file diff --git a/translations/ko/1-Introduction/1-intro-to-ML/README.md b/translations/ko/1-Introduction/1-intro-to-ML/README.md index a2eaa1ec2..b130b9f86 100644 --- a/translations/ko/1-Introduction/1-intro-to-ML/README.md +++ b/translations/ko/1-Introduction/1-intro-to-ML/README.md @@ -1,12 +1,3 @@ - # 머신 러닝 소개 ## [강의 전 퀴즈](https://ff-quizzes.netlify.app/en/ml/) diff --git a/translations/ko/1-Introduction/1-intro-to-ML/assignment.md b/translations/ko/1-Introduction/1-intro-to-ML/assignment.md index 2ebfce06a..a14b46502 100644 --- a/translations/ko/1-Introduction/1-intro-to-ML/assignment.md +++ b/translations/ko/1-Introduction/1-intro-to-ML/assignment.md @@ -1,12 +1,3 @@ - # 시작하기 ## 지침 diff --git a/translations/ko/1-Introduction/2-history-of-ML/README.md b/translations/ko/1-Introduction/2-history-of-ML/README.md index 1692ffc9f..929c93fb1 100644 --- a/translations/ko/1-Introduction/2-history-of-ML/README.md +++ b/translations/ko/1-Introduction/2-history-of-ML/README.md @@ -1,12 +1,3 @@ - # 머신 러닝의 역사 ![머신 러닝 역사의 요약 스케치노트](../../../../sketchnotes/ml-history.png) diff --git a/translations/ko/1-Introduction/2-history-of-ML/assignment.md b/translations/ko/1-Introduction/2-history-of-ML/assignment.md index 9ae581442..215e97e48 100644 --- a/translations/ko/1-Introduction/2-history-of-ML/assignment.md +++ b/translations/ko/1-Introduction/2-history-of-ML/assignment.md @@ -1,12 +1,3 @@ - # 타임라인 만들기 ## 지침 diff --git a/translations/ko/1-Introduction/3-fairness/README.md b/translations/ko/1-Introduction/3-fairness/README.md index faab55991..a677d6917 100644 --- a/translations/ko/1-Introduction/3-fairness/README.md +++ b/translations/ko/1-Introduction/3-fairness/README.md @@ -1,12 +1,3 @@ - # 책임 있는 AI를 활용한 머신 러닝 솔루션 구축 ![머신 러닝에서 책임 있는 AI의 요약을 담은 스케치노트](../../../../sketchnotes/ml-fairness.png) diff --git a/translations/ko/1-Introduction/3-fairness/assignment.md b/translations/ko/1-Introduction/3-fairness/assignment.md index d36cb3cfb..d4cda2ba4 100644 --- a/translations/ko/1-Introduction/3-fairness/assignment.md +++ b/translations/ko/1-Introduction/3-fairness/assignment.md @@ -1,12 +1,3 @@ - # 책임 있는 AI 도구 상자 탐색하기 ## 지침 diff --git a/translations/ko/1-Introduction/4-techniques-of-ML/README.md b/translations/ko/1-Introduction/4-techniques-of-ML/README.md index 0994e8c43..e928eb920 100644 --- a/translations/ko/1-Introduction/4-techniques-of-ML/README.md +++ b/translations/ko/1-Introduction/4-techniques-of-ML/README.md @@ -1,12 +1,3 @@ - # 머신 러닝 기법 머신 러닝 모델을 구축, 사용, 유지 관리하는 과정과 그 모델이 사용하는 데이터는 다른 개발 워크플로우와 매우 다릅니다. 이번 강의에서는 이 과정을 이해하기 쉽게 설명하고, 알아야 할 주요 기법들을 정리합니다. 여러분은 다음을 배우게 됩니다: diff --git a/translations/ko/1-Introduction/4-techniques-of-ML/assignment.md b/translations/ko/1-Introduction/4-techniques-of-ML/assignment.md index 0023610e2..540982200 100644 --- a/translations/ko/1-Introduction/4-techniques-of-ML/assignment.md +++ b/translations/ko/1-Introduction/4-techniques-of-ML/assignment.md @@ -1,12 +1,3 @@ - # 데이터 과학자 인터뷰 ## 지침 diff --git a/translations/ko/1-Introduction/README.md b/translations/ko/1-Introduction/README.md index 872c345b5..1febccd68 100644 --- a/translations/ko/1-Introduction/README.md +++ b/translations/ko/1-Introduction/README.md @@ -1,12 +1,3 @@ - # 머신 러닝 소개 이 커리큘럼 섹션에서는 머신 러닝 분야의 기본 개념, 그것이 무엇인지, 그리고 연구자들이 이를 다루기 위해 사용하는 기술에 대해 배우게 됩니다. 함께 이 새로운 ML 세계를 탐험해 봅시다! diff --git a/translations/ko/2-Regression/1-Tools/README.md b/translations/ko/2-Regression/1-Tools/README.md index 1f2f3f402..859336ef6 100644 --- a/translations/ko/2-Regression/1-Tools/README.md +++ b/translations/ko/2-Regression/1-Tools/README.md @@ -1,12 +1,3 @@ - # Python과 Scikit-learn으로 회귀 모델 시작하기 ![스케치노트로 요약된 회귀](../../../../sketchnotes/ml-regression.png) diff --git a/translations/ko/2-Regression/1-Tools/assignment.md b/translations/ko/2-Regression/1-Tools/assignment.md index 339608e65..be6e2dc19 100644 --- a/translations/ko/2-Regression/1-Tools/assignment.md +++ b/translations/ko/2-Regression/1-Tools/assignment.md @@ -1,12 +1,3 @@ - # Scikit-learn을 사용한 회귀 분석 ## 지침 diff --git a/translations/ko/2-Regression/1-Tools/solution/Julia/README.md b/translations/ko/2-Regression/1-Tools/solution/Julia/README.md index 70a056a2c..1e54706d7 100644 --- a/translations/ko/2-Regression/1-Tools/solution/Julia/README.md +++ b/translations/ko/2-Regression/1-Tools/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ko/2-Regression/2-Data/README.md b/translations/ko/2-Regression/2-Data/README.md index 81b7aa88a..f8266cfd7 100644 --- a/translations/ko/2-Regression/2-Data/README.md +++ b/translations/ko/2-Regression/2-Data/README.md @@ -1,12 +1,3 @@ - # Scikit-learn을 사용한 회귀 모델 구축: 데이터 준비 및 시각화 ![데이터 시각화 인포그래픽](../../../../2-Regression/2-Data/images/data-visualization.png) diff --git a/translations/ko/2-Regression/2-Data/assignment.md b/translations/ko/2-Regression/2-Data/assignment.md index dc820fe19..52eea8c57 100644 --- a/translations/ko/2-Regression/2-Data/assignment.md +++ b/translations/ko/2-Regression/2-Data/assignment.md @@ -1,12 +1,3 @@ - # 시각화 탐구 데이터 시각화를 위해 사용할 수 있는 다양한 라이브러리가 있습니다. 이 강의의 Pumpkin 데이터를 사용하여 샘플 노트북에서 matplotlib과 seaborn을 활용해 몇 가지 시각화를 만들어 보세요. 어떤 라이브러리가 더 사용하기 쉬운가요? diff --git a/translations/ko/2-Regression/2-Data/solution/Julia/README.md b/translations/ko/2-Regression/2-Data/solution/Julia/README.md index fc797b4e2..c1a16076d 100644 --- a/translations/ko/2-Regression/2-Data/solution/Julia/README.md +++ b/translations/ko/2-Regression/2-Data/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ko/2-Regression/3-Linear/README.md b/translations/ko/2-Regression/3-Linear/README.md index 51f348a85..740506be3 100644 --- a/translations/ko/2-Regression/3-Linear/README.md +++ b/translations/ko/2-Regression/3-Linear/README.md @@ -1,12 +1,3 @@ - # Scikit-learn을 사용하여 회귀 모델 구축: 네 가지 방법으로 회귀 분석하기 ![선형 회귀와 다항 회귀 인포그래픽](../../../../2-Regression/3-Linear/images/linear-polynomial.png) @@ -115,11 +106,11 @@ day_of_year = pd.to_datetime(pumpkins['Date']).apply(lambda dt: (dt-datetime(dt. 이전 강의에서 보았듯이, 월별 평균 가격은 다음과 같습니다: -월별 평균 가격 +월별 평균 가격 이는 상관관계가 있을 가능성을 시사하며, `Month`와 `Price` 또는 `DayOfYear`와 `Price` 간의 관계를 예측하기 위해 선형 회귀 모델을 훈련시킬 수 있습니다. 아래는 후자의 관계를 보여주는 산점도입니다: -가격 vs 연도의 일수 산점도 +가격 vs 연도의 일수 산점도 `corr` 함수를 사용하여 상관관계를 확인해 봅시다: @@ -138,7 +129,7 @@ for i,var in enumerate(new_pumpkins['Variety'].unique()): ax = df.plot.scatter('DayOfYear','Price',ax=ax,c=colors[i],label=var) ``` -가격 vs 연도의 일수 산점도 +가격 vs 연도의 일수 산점도 조사 결과, 판매 날짜보다 품종이 전체 가격에 더 큰 영향을 미친다는 것을 알 수 있습니다. 이를 막대 그래프로 확인할 수 있습니다: @@ -146,7 +137,7 @@ for i,var in enumerate(new_pumpkins['Variety'].unique()): new_pumpkins.groupby('Variety')['Price'].mean().plot(kind='bar') ``` -품종별 가격 막대 그래프 +품종별 가격 막대 그래프 이제 '파이 타입'이라는 특정 호박 품종에만 집중하여 날짜가 가격에 미치는 영향을 살펴봅시다: @@ -154,7 +145,7 @@ new_pumpkins.groupby('Variety')['Price'].mean().plot(kind='bar') pie_pumpkins = new_pumpkins[new_pumpkins['Variety']=='PIE TYPE'] pie_pumpkins.plot.scatter('DayOfYear','Price') ``` -파이 호박 가격 vs 연도의 일수 산점도 +파이 호박 가격 vs 연도의 일수 산점도 이제 `corr` 함수를 사용하여 `Price`와 `DayOfYear` 간의 상관관계를 계산하면 `-0.27` 정도의 값을 얻을 수 있습니다. 이는 예측 모델을 훈련시키는 것이 의미가 있음을 나타냅니다. @@ -228,7 +219,7 @@ plt.scatter(X_test,y_test) plt.plot(X_test,pred) ``` -선형 회귀 +선형 회귀 ## 다항 회귀 @@ -257,7 +248,7 @@ pipeline.fit(X_train,y_train) 파이프라인은 원래의 `LinearRegression` 객체와 동일한 방식으로 사용할 수 있습니다. 즉, 파이프라인을 `fit`하고, 그런 다음 `predict`를 사용하여 예측 결과를 얻을 수 있습니다. 아래는 테스트 데이터와 근사 곡선을 보여주는 그래프입니다: -다항 회귀 +다항 회귀 다항 회귀를 사용하면 약간 낮은 MSE와 약간 높은 결정 계수를 얻을 수 있지만, 큰 차이는 없습니다. 다른 특성을 고려해야 합니다! @@ -275,7 +266,7 @@ pipeline.fit(X_train,y_train) 여기에서 평균 가격이 종류에 따라 어떻게 달라지는지 확인할 수 있습니다: -종류별 평균 가격 +종류별 평균 가격 종류를 고려하려면 먼저 이를 숫자 형태로 변환하거나 **인코딩**해야 합니다. 이를 수행하는 몇 가지 방법이 있습니다: diff --git a/translations/ko/2-Regression/3-Linear/assignment.md b/translations/ko/2-Regression/3-Linear/assignment.md index 9761e2167..ca55c2b78 100644 --- a/translations/ko/2-Regression/3-Linear/assignment.md +++ b/translations/ko/2-Regression/3-Linear/assignment.md @@ -1,12 +1,3 @@ - # 회귀 모델 생성하기 ## 지침 diff --git a/translations/ko/2-Regression/3-Linear/solution/Julia/README.md b/translations/ko/2-Regression/3-Linear/solution/Julia/README.md index a23d17437..0463fbc5a 100644 --- a/translations/ko/2-Regression/3-Linear/solution/Julia/README.md +++ b/translations/ko/2-Regression/3-Linear/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ko/2-Regression/4-Logistic/README.md b/translations/ko/2-Regression/4-Logistic/README.md index 411dbae5b..3391817e8 100644 --- a/translations/ko/2-Regression/4-Logistic/README.md +++ b/translations/ko/2-Regression/4-Logistic/README.md @@ -1,12 +1,3 @@ - # 카테고리 예측을 위한 로지스틱 회귀 ![로지스틱 vs. 선형 회귀 인포그래픽](../../../../2-Regression/4-Logistic/images/linear-vs-logistic.png) diff --git a/translations/ko/2-Regression/4-Logistic/assignment.md b/translations/ko/2-Regression/4-Logistic/assignment.md index fe23f1aa4..a13c8122d 100644 --- a/translations/ko/2-Regression/4-Logistic/assignment.md +++ b/translations/ko/2-Regression/4-Logistic/assignment.md @@ -1,12 +1,3 @@ - # 회귀 재시도 ## 지침 diff --git a/translations/ko/2-Regression/4-Logistic/solution/Julia/README.md b/translations/ko/2-Regression/4-Logistic/solution/Julia/README.md index 67e98094d..03d4f684f 100644 --- a/translations/ko/2-Regression/4-Logistic/solution/Julia/README.md +++ b/translations/ko/2-Regression/4-Logistic/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ko/2-Regression/README.md b/translations/ko/2-Regression/README.md index ddd577037..63f07b3be 100644 --- a/translations/ko/2-Regression/README.md +++ b/translations/ko/2-Regression/README.md @@ -1,12 +1,3 @@ - # 머신 러닝을 위한 회귀 모델 ## 지역 주제: 북미 지역 호박 가격을 위한 회귀 모델 🎃 diff --git a/translations/ko/3-Web-App/1-Web-App/README.md b/translations/ko/3-Web-App/1-Web-App/README.md index 902450ad4..55aaeff09 100644 --- a/translations/ko/3-Web-App/1-Web-App/README.md +++ b/translations/ko/3-Web-App/1-Web-App/README.md @@ -1,12 +1,3 @@ - # 웹 앱을 만들어 ML 모델 사용하기 이 강의에서는 _지난 세기 동안의 UFO 목격_ 데이터를 사용하여 ML 모델을 훈련시킬 것입니다. 이 데이터는 NUFORC의 데이터베이스에서 가져왔습니다. diff --git a/translations/ko/3-Web-App/1-Web-App/assignment.md b/translations/ko/3-Web-App/1-Web-App/assignment.md index 41327cc32..8de1c9c31 100644 --- a/translations/ko/3-Web-App/1-Web-App/assignment.md +++ b/translations/ko/3-Web-App/1-Web-App/assignment.md @@ -1,12 +1,3 @@ - # 다른 모델 시도하기 ## 지침 diff --git a/translations/ko/3-Web-App/README.md b/translations/ko/3-Web-App/README.md index 10c42d586..717c3800f 100644 --- a/translations/ko/3-Web-App/README.md +++ b/translations/ko/3-Web-App/README.md @@ -1,12 +1,3 @@ - # ML 모델을 활용한 웹 앱 만들기 이 커리큘럼 섹션에서는 Scikit-learn 모델을 파일로 저장하여 웹 애플리케이션 내에서 예측에 사용할 수 있는 방법을 배우는 실용적인 머신러닝 주제를 소개합니다. 모델을 저장한 후에는 Flask로 구축된 웹 앱에서 이를 사용하는 방법을 배우게 됩니다. 먼저 UFO 목격 데이터를 사용하여 모델을 생성합니다! 그런 다음, 특정 시간(초)과 위도 및 경도 값을 입력하여 어느 국가에서 UFO를 목격했는지 예측할 수 있는 웹 앱을 구축합니다. diff --git a/translations/ko/4-Classification/1-Introduction/README.md b/translations/ko/4-Classification/1-Introduction/README.md index a4dbd4e91..36fbd6f3a 100644 --- a/translations/ko/4-Classification/1-Introduction/README.md +++ b/translations/ko/4-Classification/1-Introduction/README.md @@ -1,12 +1,3 @@ - # 분류 소개 이 네 가지 강의에서는 고전적인 머신 러닝의 핵심 주제인 _분류_를 탐구합니다. 아시아와 인도의 다양한 요리 데이터를 사용하여 여러 분류 알고리즘을 살펴볼 것입니다. 배가 고프셨다면 잘 오셨습니다! diff --git a/translations/ko/4-Classification/1-Introduction/assignment.md b/translations/ko/4-Classification/1-Introduction/assignment.md index 9dde85b51..17305502e 100644 --- a/translations/ko/4-Classification/1-Introduction/assignment.md +++ b/translations/ko/4-Classification/1-Introduction/assignment.md @@ -1,12 +1,3 @@ - # 분류 방법 탐구 ## 지침 diff --git a/translations/ko/4-Classification/1-Introduction/solution/Julia/README.md b/translations/ko/4-Classification/1-Introduction/solution/Julia/README.md index dfada7543..31b726d91 100644 --- a/translations/ko/4-Classification/1-Introduction/solution/Julia/README.md +++ b/translations/ko/4-Classification/1-Introduction/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ko/4-Classification/2-Classifiers-1/README.md b/translations/ko/4-Classification/2-Classifiers-1/README.md index 320ef4c1b..00102fffe 100644 --- a/translations/ko/4-Classification/2-Classifiers-1/README.md +++ b/translations/ko/4-Classification/2-Classifiers-1/README.md @@ -1,12 +1,3 @@ - # 요리 분류기 1 이 강의에서는 이전 강의에서 저장한 균형 잡히고 깨끗한 요리 데이터셋을 사용합니다. diff --git a/translations/ko/4-Classification/2-Classifiers-1/assignment.md b/translations/ko/4-Classification/2-Classifiers-1/assignment.md index c4ec7bbac..3a15df836 100644 --- a/translations/ko/4-Classification/2-Classifiers-1/assignment.md +++ b/translations/ko/4-Classification/2-Classifiers-1/assignment.md @@ -1,12 +1,3 @@ - # 해결 방법 연구하기 ## 지침 diff --git a/translations/ko/4-Classification/2-Classifiers-1/solution/Julia/README.md b/translations/ko/4-Classification/2-Classifiers-1/solution/Julia/README.md index 006fbde46..31b726d91 100644 --- a/translations/ko/4-Classification/2-Classifiers-1/solution/Julia/README.md +++ b/translations/ko/4-Classification/2-Classifiers-1/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ko/4-Classification/3-Classifiers-2/README.md b/translations/ko/4-Classification/3-Classifiers-2/README.md index 04484cbb8..348b314fe 100644 --- a/translations/ko/4-Classification/3-Classifiers-2/README.md +++ b/translations/ko/4-Classification/3-Classifiers-2/README.md @@ -1,12 +1,3 @@ - # 요리 분류기 2 이 두 번째 분류 수업에서는 숫자 데이터를 분류하는 더 많은 방법을 탐구합니다. 또한 하나의 분류기를 선택하는 것이 다른 분류기를 선택하는 것에 비해 어떤 영향을 미치는지 배우게 됩니다. diff --git a/translations/ko/4-Classification/3-Classifiers-2/assignment.md b/translations/ko/4-Classification/3-Classifiers-2/assignment.md index 9c8222bc6..d5c3e21f6 100644 --- a/translations/ko/4-Classification/3-Classifiers-2/assignment.md +++ b/translations/ko/4-Classification/3-Classifiers-2/assignment.md @@ -1,12 +1,3 @@ - # 매개변수 활용 ## 지침 diff --git a/translations/ko/4-Classification/3-Classifiers-2/solution/Julia/README.md b/translations/ko/4-Classification/3-Classifiers-2/solution/Julia/README.md index b1f7188fe..3ce376437 100644 --- a/translations/ko/4-Classification/3-Classifiers-2/solution/Julia/README.md +++ b/translations/ko/4-Classification/3-Classifiers-2/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ko/4-Classification/4-Applied/README.md b/translations/ko/4-Classification/4-Applied/README.md index 223f1ff70..776a86383 100644 --- a/translations/ko/4-Classification/4-Applied/README.md +++ b/translations/ko/4-Classification/4-Applied/README.md @@ -1,12 +1,3 @@ - # 요리 추천 웹 앱 만들기 이 강의에서는 이전 강의에서 배운 기술과 이 시리즈에서 사용된 맛있는 요리 데이터셋을 활용하여 분류 모델을 구축합니다. 또한 저장된 모델을 사용하여 Onnx의 웹 런타임을 활용한 작은 웹 앱을 만들 것입니다. diff --git a/translations/ko/4-Classification/4-Applied/assignment.md b/translations/ko/4-Classification/4-Applied/assignment.md index 7c0070113..f54859648 100644 --- a/translations/ko/4-Classification/4-Applied/assignment.md +++ b/translations/ko/4-Classification/4-Applied/assignment.md @@ -1,12 +1,3 @@ - # 추천 시스템 만들기 ## 지침 diff --git a/translations/ko/4-Classification/README.md b/translations/ko/4-Classification/README.md index ea712e384..0a23b82c0 100644 --- a/translations/ko/4-Classification/README.md +++ b/translations/ko/4-Classification/README.md @@ -1,12 +1,3 @@ - # 분류 시작하기 ## 지역 주제: 맛있는 아시아 및 인도 요리 🍜 diff --git a/translations/ko/5-Clustering/1-Visualize/README.md b/translations/ko/5-Clustering/1-Visualize/README.md index c7701fb66..e476b8d72 100644 --- a/translations/ko/5-Clustering/1-Visualize/README.md +++ b/translations/ko/5-Clustering/1-Visualize/README.md @@ -1,12 +1,3 @@ - # 클러스터링 소개 클러스터링은 데이터셋이 라벨이 없거나 입력값이 미리 정의된 출력값과 매칭되지 않는다고 가정하는 [비지도 학습](https://wikipedia.org/wiki/Unsupervised_learning)의 한 유형입니다. 클러스터링은 다양한 알고리즘을 사용하여 라벨이 없는 데이터를 분류하고, 데이터에서 감지된 패턴에 따라 그룹을 제공합니다. diff --git a/translations/ko/5-Clustering/1-Visualize/assignment.md b/translations/ko/5-Clustering/1-Visualize/assignment.md index 2e160282f..290f9e429 100644 --- a/translations/ko/5-Clustering/1-Visualize/assignment.md +++ b/translations/ko/5-Clustering/1-Visualize/assignment.md @@ -1,12 +1,3 @@ - # 클러스터링을 위한 다른 시각화 방법 연구 ## 지침 diff --git a/translations/ko/5-Clustering/1-Visualize/solution/Julia/README.md b/translations/ko/5-Clustering/1-Visualize/solution/Julia/README.md index de4518e43..0463fbc5a 100644 --- a/translations/ko/5-Clustering/1-Visualize/solution/Julia/README.md +++ b/translations/ko/5-Clustering/1-Visualize/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ko/5-Clustering/2-K-Means/README.md b/translations/ko/5-Clustering/2-K-Means/README.md index b5d7a4beb..f1b2bc889 100644 --- a/translations/ko/5-Clustering/2-K-Means/README.md +++ b/translations/ko/5-Clustering/2-K-Means/README.md @@ -1,12 +1,3 @@ - # K-Means 클러스터링 ## [강의 전 퀴즈](https://ff-quizzes.netlify.app/en/ml/) diff --git a/translations/ko/5-Clustering/2-K-Means/assignment.md b/translations/ko/5-Clustering/2-K-Means/assignment.md index b87d26a23..9effc5aae 100644 --- a/translations/ko/5-Clustering/2-K-Means/assignment.md +++ b/translations/ko/5-Clustering/2-K-Means/assignment.md @@ -1,12 +1,3 @@ - # 다양한 클러스터링 방법 시도하기 ## 지침 diff --git a/translations/ko/5-Clustering/2-K-Means/solution/Julia/README.md b/translations/ko/5-Clustering/2-K-Means/solution/Julia/README.md index e6f696fa3..31b726d91 100644 --- a/translations/ko/5-Clustering/2-K-Means/solution/Julia/README.md +++ b/translations/ko/5-Clustering/2-K-Means/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ko/5-Clustering/README.md b/translations/ko/5-Clustering/README.md index 374ce19d3..9e0dd9807 100644 --- a/translations/ko/5-Clustering/README.md +++ b/translations/ko/5-Clustering/README.md @@ -1,12 +1,3 @@ - # 머신 러닝을 위한 클러스터링 모델 클러스터링은 서로 비슷한 객체를 찾아 클러스터라고 불리는 그룹으로 묶는 머신 러닝 작업입니다. 클러스터링이 머신 러닝의 다른 접근 방식과 다른 점은 모든 것이 자동으로 이루어진다는 점입니다. 사실, 이는 지도 학습(supervised learning)의 반대라고 할 수 있습니다. diff --git a/translations/ko/6-NLP/1-Introduction-to-NLP/README.md b/translations/ko/6-NLP/1-Introduction-to-NLP/README.md index 23edb13b0..a58cfebb5 100644 --- a/translations/ko/6-NLP/1-Introduction-to-NLP/README.md +++ b/translations/ko/6-NLP/1-Introduction-to-NLP/README.md @@ -1,12 +1,3 @@ - # 자연어 처리 소개 이 강의에서는 *계산 언어학*의 하위 분야인 *자연어 처리*의 간략한 역사와 중요한 개념을 다룹니다. diff --git a/translations/ko/6-NLP/1-Introduction-to-NLP/assignment.md b/translations/ko/6-NLP/1-Introduction-to-NLP/assignment.md index c1f9ac0dd..31afbb7a1 100644 --- a/translations/ko/6-NLP/1-Introduction-to-NLP/assignment.md +++ b/translations/ko/6-NLP/1-Introduction-to-NLP/assignment.md @@ -1,12 +1,3 @@ - # 봇 찾기 ## 지침 diff --git a/translations/ko/6-NLP/2-Tasks/README.md b/translations/ko/6-NLP/2-Tasks/README.md index 55be7fa49..614d80584 100644 --- a/translations/ko/6-NLP/2-Tasks/README.md +++ b/translations/ko/6-NLP/2-Tasks/README.md @@ -1,12 +1,3 @@ - # 자연어 처리의 일반적인 작업과 기술 대부분의 *자연어 처리* 작업에서는 처리할 텍스트를 분해하고, 분석하며, 결과를 저장하거나 규칙 및 데이터 세트와 교차 참조해야 합니다. 이러한 작업을 통해 프로그래머는 텍스트에서 _의미_, _의도_, 또는 단순히 _단어 빈도_를 도출할 수 있습니다. diff --git a/translations/ko/6-NLP/2-Tasks/assignment.md b/translations/ko/6-NLP/2-Tasks/assignment.md index d65dc432c..870798b33 100644 --- a/translations/ko/6-NLP/2-Tasks/assignment.md +++ b/translations/ko/6-NLP/2-Tasks/assignment.md @@ -1,12 +1,3 @@ - # 봇에게 대답하게 만들기 ## 지침 diff --git a/translations/ko/6-NLP/3-Translation-Sentiment/README.md b/translations/ko/6-NLP/3-Translation-Sentiment/README.md index 8160d447e..fad1be797 100644 --- a/translations/ko/6-NLP/3-Translation-Sentiment/README.md +++ b/translations/ko/6-NLP/3-Translation-Sentiment/README.md @@ -1,12 +1,3 @@ - # 기계 학습을 활용한 번역 및 감정 분석 이전 강의에서는 `TextBlob` 라이브러리를 사용하여 기본적인 NLP 작업(예: 명사구 추출)을 수행하는 간단한 봇을 만드는 방법을 배웠습니다. `TextBlob`은 기계 학습을 백그라운드에서 활용합니다. 계산 언어학에서 또 다른 중요한 과제는 문장을 한 언어에서 다른 언어로 정확하게 _번역_하는 것입니다. diff --git a/translations/ko/6-NLP/3-Translation-Sentiment/assignment.md b/translations/ko/6-NLP/3-Translation-Sentiment/assignment.md index 46c8b6ede..9795c8a26 100644 --- a/translations/ko/6-NLP/3-Translation-Sentiment/assignment.md +++ b/translations/ko/6-NLP/3-Translation-Sentiment/assignment.md @@ -1,12 +1,3 @@ - # 시적 허용 ## 지침 diff --git a/translations/ko/6-NLP/3-Translation-Sentiment/solution/Julia/README.md b/translations/ko/6-NLP/3-Translation-Sentiment/solution/Julia/README.md index 85d8d16d3..17dad44ea 100644 --- a/translations/ko/6-NLP/3-Translation-Sentiment/solution/Julia/README.md +++ b/translations/ko/6-NLP/3-Translation-Sentiment/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ko/6-NLP/3-Translation-Sentiment/solution/R/README.md b/translations/ko/6-NLP/3-Translation-Sentiment/solution/R/README.md index 7d5a3df68..31b726d91 100644 --- a/translations/ko/6-NLP/3-Translation-Sentiment/solution/R/README.md +++ b/translations/ko/6-NLP/3-Translation-Sentiment/solution/R/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ko/6-NLP/4-Hotel-Reviews-1/README.md b/translations/ko/6-NLP/4-Hotel-Reviews-1/README.md index be3c626b2..e5553f8ad 100644 --- a/translations/ko/6-NLP/4-Hotel-Reviews-1/README.md +++ b/translations/ko/6-NLP/4-Hotel-Reviews-1/README.md @@ -1,12 +1,3 @@ - # 호텔 리뷰를 활용한 감정 분석 - 데이터 처리 이 섹션에서는 이전 강의에서 배운 기술을 활용하여 대규모 데이터셋에 대한 탐색적 데이터 분석을 수행합니다. 다양한 열의 유용성을 충분히 이해한 후, 다음을 배우게 됩니다: diff --git a/translations/ko/6-NLP/4-Hotel-Reviews-1/assignment.md b/translations/ko/6-NLP/4-Hotel-Reviews-1/assignment.md index 38327247f..302eef20c 100644 --- a/translations/ko/6-NLP/4-Hotel-Reviews-1/assignment.md +++ b/translations/ko/6-NLP/4-Hotel-Reviews-1/assignment.md @@ -1,12 +1,3 @@ - # NLTK ## 지침 diff --git a/translations/ko/6-NLP/4-Hotel-Reviews-1/solution/Julia/README.md b/translations/ko/6-NLP/4-Hotel-Reviews-1/solution/Julia/README.md index e1e22163c..aa43867a2 100644 --- a/translations/ko/6-NLP/4-Hotel-Reviews-1/solution/Julia/README.md +++ b/translations/ko/6-NLP/4-Hotel-Reviews-1/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ko/6-NLP/4-Hotel-Reviews-1/solution/R/README.md b/translations/ko/6-NLP/4-Hotel-Reviews-1/solution/R/README.md index 5e8b3ab10..31b726d91 100644 --- a/translations/ko/6-NLP/4-Hotel-Reviews-1/solution/R/README.md +++ b/translations/ko/6-NLP/4-Hotel-Reviews-1/solution/R/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ko/6-NLP/5-Hotel-Reviews-2/README.md b/translations/ko/6-NLP/5-Hotel-Reviews-2/README.md index ed55ddb9c..848173e40 100644 --- a/translations/ko/6-NLP/5-Hotel-Reviews-2/README.md +++ b/translations/ko/6-NLP/5-Hotel-Reviews-2/README.md @@ -1,12 +1,3 @@ - # 호텔 리뷰를 활용한 감정 분석 데이터셋을 자세히 탐색한 후, 이제 열을 필터링하고 NLP 기술을 사용하여 호텔에 대한 새로운 인사이트를 얻을 때입니다. diff --git a/translations/ko/6-NLP/5-Hotel-Reviews-2/assignment.md b/translations/ko/6-NLP/5-Hotel-Reviews-2/assignment.md index e0a637989..7fdd27171 100644 --- a/translations/ko/6-NLP/5-Hotel-Reviews-2/assignment.md +++ b/translations/ko/6-NLP/5-Hotel-Reviews-2/assignment.md @@ -1,12 +1,3 @@ - # 다른 데이터셋 시도하기 ## 지침 diff --git a/translations/ko/6-NLP/5-Hotel-Reviews-2/solution/Julia/README.md b/translations/ko/6-NLP/5-Hotel-Reviews-2/solution/Julia/README.md index dcd13373c..17dad44ea 100644 --- a/translations/ko/6-NLP/5-Hotel-Reviews-2/solution/Julia/README.md +++ b/translations/ko/6-NLP/5-Hotel-Reviews-2/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ko/6-NLP/5-Hotel-Reviews-2/solution/R/README.md b/translations/ko/6-NLP/5-Hotel-Reviews-2/solution/R/README.md index 591420cad..31b726d91 100644 --- a/translations/ko/6-NLP/5-Hotel-Reviews-2/solution/R/README.md +++ b/translations/ko/6-NLP/5-Hotel-Reviews-2/solution/R/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ko/6-NLP/README.md b/translations/ko/6-NLP/README.md index accc62364..47941ed4f 100644 --- a/translations/ko/6-NLP/README.md +++ b/translations/ko/6-NLP/README.md @@ -1,12 +1,3 @@ - # 자연어 처리 시작하기 자연어 처리(NLP)는 컴퓨터 프로그램이 인간의 언어를 이해할 수 있도록 하는 기술로, 말하거나 쓰여진 형태의 자연어를 이해하는 능력을 말합니다. 이는 인공지능(AI)의 한 구성 요소입니다. NLP는 50년 이상 존재해왔으며, 언어학 분야에 뿌리를 두고 있습니다. 이 분야는 기계가 인간의 언어를 이해하고 처리할 수 있도록 돕는 데 초점이 맞춰져 있습니다. 이를 통해 맞춤법 검사나 기계 번역과 같은 작업을 수행할 수 있습니다. NLP는 의료 연구, 검색 엔진, 비즈니스 인텔리전스 등 다양한 분야에서 실질적인 응용 사례를 가지고 있습니다. diff --git a/translations/ko/6-NLP/data/README.md b/translations/ko/6-NLP/data/README.md index 524127fbb..a31b28154 100644 --- a/translations/ko/6-NLP/data/README.md +++ b/translations/ko/6-NLP/data/README.md @@ -1,12 +1,3 @@ - 이 폴더에 호텔 리뷰 데이터를 다운로드하세요. --- diff --git a/translations/ko/7-TimeSeries/1-Introduction/README.md b/translations/ko/7-TimeSeries/1-Introduction/README.md index bc6e654aa..27a312f61 100644 --- a/translations/ko/7-TimeSeries/1-Introduction/README.md +++ b/translations/ko/7-TimeSeries/1-Introduction/README.md @@ -1,12 +1,3 @@ - # 시계열 예측 소개 ![스케치노트로 본 시계열 요약](../../../../sketchnotes/ml-timeseries.png) diff --git a/translations/ko/7-TimeSeries/1-Introduction/assignment.md b/translations/ko/7-TimeSeries/1-Introduction/assignment.md index eee0d8fda..0a44c0351 100644 --- a/translations/ko/7-TimeSeries/1-Introduction/assignment.md +++ b/translations/ko/7-TimeSeries/1-Introduction/assignment.md @@ -1,12 +1,3 @@ - # 몇 가지 추가적인 시계열 데이터 시각화 ## 지침 diff --git a/translations/ko/7-TimeSeries/1-Introduction/solution/Julia/README.md b/translations/ko/7-TimeSeries/1-Introduction/solution/Julia/README.md index 976ba3bb1..c1a16076d 100644 --- a/translations/ko/7-TimeSeries/1-Introduction/solution/Julia/README.md +++ b/translations/ko/7-TimeSeries/1-Introduction/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ko/7-TimeSeries/1-Introduction/solution/R/README.md b/translations/ko/7-TimeSeries/1-Introduction/solution/R/README.md index c8ad7644f..1e54706d7 100644 --- a/translations/ko/7-TimeSeries/1-Introduction/solution/R/README.md +++ b/translations/ko/7-TimeSeries/1-Introduction/solution/R/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ko/7-TimeSeries/2-ARIMA/README.md b/translations/ko/7-TimeSeries/2-ARIMA/README.md index 7b613a7a8..1cbe03333 100644 --- a/translations/ko/7-TimeSeries/2-ARIMA/README.md +++ b/translations/ko/7-TimeSeries/2-ARIMA/README.md @@ -1,12 +1,3 @@ - # ARIMA를 활용한 시계열 예측 이전 강의에서는 시계열 예측에 대해 간단히 배우고 특정 기간 동안 전력 부하의 변동을 보여주는 데이터를 로드했습니다. diff --git a/translations/ko/7-TimeSeries/2-ARIMA/assignment.md b/translations/ko/7-TimeSeries/2-ARIMA/assignment.md index 89afe9667..94558fe80 100644 --- a/translations/ko/7-TimeSeries/2-ARIMA/assignment.md +++ b/translations/ko/7-TimeSeries/2-ARIMA/assignment.md @@ -1,12 +1,3 @@ - # 새로운 ARIMA 모델 ## 지침 diff --git a/translations/ko/7-TimeSeries/2-ARIMA/solution/Julia/README.md b/translations/ko/7-TimeSeries/2-ARIMA/solution/Julia/README.md index 9dc5a9beb..03d4f684f 100644 --- a/translations/ko/7-TimeSeries/2-ARIMA/solution/Julia/README.md +++ b/translations/ko/7-TimeSeries/2-ARIMA/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ko/7-TimeSeries/2-ARIMA/solution/R/README.md b/translations/ko/7-TimeSeries/2-ARIMA/solution/R/README.md index 5a9a00c06..31b726d91 100644 --- a/translations/ko/7-TimeSeries/2-ARIMA/solution/R/README.md +++ b/translations/ko/7-TimeSeries/2-ARIMA/solution/R/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ko/7-TimeSeries/3-SVR/README.md b/translations/ko/7-TimeSeries/3-SVR/README.md index afa8b00c1..d6eae9ccb 100644 --- a/translations/ko/7-TimeSeries/3-SVR/README.md +++ b/translations/ko/7-TimeSeries/3-SVR/README.md @@ -1,12 +1,3 @@ - # 서포트 벡터 회귀(Support Vector Regressor)를 활용한 시계열 예측 이전 강의에서는 ARIMA 모델을 사용하여 시계열 예측을 수행하는 방법을 배웠습니다. 이번에는 연속 데이터를 예측하는 데 사용되는 회귀 모델인 서포트 벡터 회귀(Support Vector Regressor) 모델에 대해 알아보겠습니다. diff --git a/translations/ko/7-TimeSeries/3-SVR/assignment.md b/translations/ko/7-TimeSeries/3-SVR/assignment.md index 37f213852..2e31a3f6f 100644 --- a/translations/ko/7-TimeSeries/3-SVR/assignment.md +++ b/translations/ko/7-TimeSeries/3-SVR/assignment.md @@ -1,12 +1,3 @@ - # 새로운 SVR 모델 ## 지침 [^1] diff --git a/translations/ko/7-TimeSeries/README.md b/translations/ko/7-TimeSeries/README.md index 466cfb068..013d7f73b 100644 --- a/translations/ko/7-TimeSeries/README.md +++ b/translations/ko/7-TimeSeries/README.md @@ -1,12 +1,3 @@ - # 시계열 예측 소개 시계열 예측이란 무엇일까요? 과거의 추세를 분석하여 미래의 사건을 예측하는 것입니다. diff --git a/translations/ko/8-Reinforcement/1-QLearning/README.md b/translations/ko/8-Reinforcement/1-QLearning/README.md index 80bde9940..0999b2aa2 100644 --- a/translations/ko/8-Reinforcement/1-QLearning/README.md +++ b/translations/ko/8-Reinforcement/1-QLearning/README.md @@ -1,12 +1,3 @@ - # 강화 학습과 Q-러닝 소개 ![기계 학습에서 강화 학습 요약을 스케치노트로 표현](../../../../sketchnotes/ml-reinforcement.png) diff --git a/translations/ko/8-Reinforcement/1-QLearning/assignment.md b/translations/ko/8-Reinforcement/1-QLearning/assignment.md index ed41bcffc..55b6122f8 100644 --- a/translations/ko/8-Reinforcement/1-QLearning/assignment.md +++ b/translations/ko/8-Reinforcement/1-QLearning/assignment.md @@ -1,12 +1,3 @@ - # 더 현실적인 세계 우리의 상황에서 피터는 거의 지치거나 배고프지 않은 상태로 이동할 수 있었습니다. 더 현실적인 세계에서는 피터가 가끔씩 앉아서 쉬어야 하고, 스스로 먹을 것도 챙겨야 합니다. 다음 규칙들을 구현하여 우리의 세계를 더 현실적으로 만들어 봅시다: diff --git a/translations/ko/8-Reinforcement/1-QLearning/solution/Julia/README.md b/translations/ko/8-Reinforcement/1-QLearning/solution/Julia/README.md index 8d98f1134..fbbde1203 100644 --- a/translations/ko/8-Reinforcement/1-QLearning/solution/Julia/README.md +++ b/translations/ko/8-Reinforcement/1-QLearning/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ko/8-Reinforcement/1-QLearning/solution/R/README.md b/translations/ko/8-Reinforcement/1-QLearning/solution/R/README.md index 732549666..03d4f684f 100644 --- a/translations/ko/8-Reinforcement/1-QLearning/solution/R/README.md +++ b/translations/ko/8-Reinforcement/1-QLearning/solution/R/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ko/8-Reinforcement/2-Gym/README.md b/translations/ko/8-Reinforcement/2-Gym/README.md index 73c733e6e..644125a10 100644 --- a/translations/ko/8-Reinforcement/2-Gym/README.md +++ b/translations/ko/8-Reinforcement/2-Gym/README.md @@ -1,12 +1,3 @@ - ## 사전 준비 이번 강의에서는 **OpenAI Gym**이라는 라이브러리를 사용하여 다양한 **환경**을 시뮬레이션할 것입니다. 이 강의의 코드는 로컬 환경(예: Visual Studio Code)에서 실행할 수 있으며, 이 경우 시뮬레이션이 새 창에서 열립니다. 온라인으로 코드를 실행할 경우, [여기](https://towardsdatascience.com/rendering-openai-gym-envs-on-binder-and-google-colab-536f99391cc7)에 설명된 대로 코드를 약간 수정해야 할 수도 있습니다. diff --git a/translations/ko/8-Reinforcement/2-Gym/assignment.md b/translations/ko/8-Reinforcement/2-Gym/assignment.md index 34c10e525..f97554fdb 100644 --- a/translations/ko/8-Reinforcement/2-Gym/assignment.md +++ b/translations/ko/8-Reinforcement/2-Gym/assignment.md @@ -1,12 +1,3 @@ - # 산악 자동차 훈련하기 [OpenAI Gym](http://gym.openai.com)은 모든 환경이 동일한 API를 제공하도록 설계되었습니다. 즉, `reset`, `step`, `render`와 같은 동일한 메서드와 **action space** 및 **observation space**의 동일한 추상화를 제공합니다. 따라서 동일한 강화 학습 알고리즘을 최소한의 코드 변경으로 다양한 환경에 적용할 수 있어야 합니다. diff --git a/translations/ko/8-Reinforcement/2-Gym/solution/Julia/README.md b/translations/ko/8-Reinforcement/2-Gym/solution/Julia/README.md index 77af4b70a..0463fbc5a 100644 --- a/translations/ko/8-Reinforcement/2-Gym/solution/Julia/README.md +++ b/translations/ko/8-Reinforcement/2-Gym/solution/Julia/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ko/8-Reinforcement/2-Gym/solution/R/README.md b/translations/ko/8-Reinforcement/2-Gym/solution/R/README.md index 8565db85e..31b726d91 100644 --- a/translations/ko/8-Reinforcement/2-Gym/solution/R/README.md +++ b/translations/ko/8-Reinforcement/2-Gym/solution/R/README.md @@ -1,12 +1,3 @@ - --- diff --git a/translations/ko/8-Reinforcement/README.md b/translations/ko/8-Reinforcement/README.md index 20cfa071d..1e9a2cb65 100644 --- a/translations/ko/8-Reinforcement/README.md +++ b/translations/ko/8-Reinforcement/README.md @@ -1,12 +1,3 @@ - # 강화 학습 소개 강화 학습(RL)은 지도 학습과 비지도 학습과 함께 기본적인 머신 러닝 패러다임 중 하나로 여겨집니다. RL은 올바른 결정을 내리거나 최소한 그로부터 배우는 데 초점이 맞춰져 있습니다. diff --git a/translations/ko/9-Real-World/1-Applications/README.md b/translations/ko/9-Real-World/1-Applications/README.md index 9a869ef75..beff8f9ce 100644 --- a/translations/ko/9-Real-World/1-Applications/README.md +++ b/translations/ko/9-Real-World/1-Applications/README.md @@ -1,12 +1,3 @@ - # 후속: 실제 세계에서의 머신 러닝 ![실제 세계에서의 머신 러닝 요약 스케치노트](../../../../sketchnotes/ml-realworld.png) diff --git a/translations/ko/9-Real-World/1-Applications/assignment.md b/translations/ko/9-Real-World/1-Applications/assignment.md index cb8c9aac9..d6da7508f 100644 --- a/translations/ko/9-Real-World/1-Applications/assignment.md +++ b/translations/ko/9-Real-World/1-Applications/assignment.md @@ -1,12 +1,3 @@ - # 머신러닝 스캐빈저 헌트 ## 지침 diff --git a/translations/ko/9-Real-World/2-Debugging-ML-Models/README.md b/translations/ko/9-Real-World/2-Debugging-ML-Models/README.md index d77682e62..dcc512d69 100644 --- a/translations/ko/9-Real-World/2-Debugging-ML-Models/README.md +++ b/translations/ko/9-Real-World/2-Debugging-ML-Models/README.md @@ -1,12 +1,3 @@ - # 후속: 책임 있는 AI 대시보드 구성 요소를 활용한 머신 러닝 모델 디버깅 ## [강의 전 퀴즈](https://ff-quizzes.netlify.app/en/ml/) diff --git a/translations/ko/9-Real-World/2-Debugging-ML-Models/assignment.md b/translations/ko/9-Real-World/2-Debugging-ML-Models/assignment.md index 41d244491..98fafc01a 100644 --- a/translations/ko/9-Real-World/2-Debugging-ML-Models/assignment.md +++ b/translations/ko/9-Real-World/2-Debugging-ML-Models/assignment.md @@ -1,12 +1,3 @@ - # 책임 있는 AI(RAI) 대시보드 탐색 ## 지침 diff --git a/translations/ko/9-Real-World/README.md b/translations/ko/9-Real-World/README.md index 90cc92249..0ea5e2419 100644 --- a/translations/ko/9-Real-World/README.md +++ b/translations/ko/9-Real-World/README.md @@ -1,12 +1,3 @@ - # 후기: 고전적 머신 러닝의 실제 응용 사례 이 커리큘럼 섹션에서는 고전적 머신 러닝의 실제 응용 사례를 소개합니다. 우리는 인터넷을 샅샅이 뒤져서 신경망, 딥러닝, AI를 최대한 배제한 채 이러한 전략을 활용한 응용 사례에 대한 백서와 기사를 찾아냈습니다. 머신 러닝이 비즈니스 시스템, 생태학적 응용, 금융, 예술과 문화 등 다양한 분야에서 어떻게 사용되는지 알아보세요. diff --git a/translations/ko/AGENTS.md b/translations/ko/AGENTS.md index f7fe678d5..5c5d260df 100644 --- a/translations/ko/AGENTS.md +++ b/translations/ko/AGENTS.md @@ -1,12 +1,3 @@ - # AGENTS.md ## 프로젝트 개요 diff --git a/translations/ko/CODE_OF_CONDUCT.md b/translations/ko/CODE_OF_CONDUCT.md index a58903b4c..4db2a21ef 100644 --- a/translations/ko/CODE_OF_CONDUCT.md +++ b/translations/ko/CODE_OF_CONDUCT.md @@ -1,12 +1,3 @@ - # Microsoft 오픈 소스 행동 강령 이 프로젝트는 [Microsoft 오픈 소스 행동 강령](https://opensource.microsoft.com/codeofconduct/)을 채택했습니다. diff --git a/translations/ko/CONTRIBUTING.md b/translations/ko/CONTRIBUTING.md index 00cad8f1a..8965fbf5e 100644 --- a/translations/ko/CONTRIBUTING.md +++ b/translations/ko/CONTRIBUTING.md @@ -1,12 +1,3 @@ - # 기여하기 이 프로젝트는 기여와 제안을 환영합니다. 대부분의 기여는 귀하가 기여자 라이선스 계약 (CLA)에 동의해야 하며, 이를 통해 귀하가 기여할 권리를 가지고 있으며 실제로 기여를 사용할 권리를 우리에게 부여한다는 것을 선언해야 합니다. 자세한 내용은 https://cla.microsoft.com을 방문하세요. diff --git a/translations/ko/README.md b/translations/ko/README.md index e4b54bf79..57d592402 100644 --- a/translations/ko/README.md +++ b/translations/ko/README.md @@ -1,12 +1,3 @@ - [![GitHub license](https://img.shields.io/github/license/microsoft/ML-For-Beginners.svg)](https://github.com/microsoft/ML-For-Beginners/blob/master/LICENSE) [![GitHub contributors](https://img.shields.io/github/contributors/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/graphs/contributors/) [![GitHub issues](https://img.shields.io/github/issues/microsoft/ML-For-Beginners.svg)](https://GitHub.com/microsoft/ML-For-Beginners/issues/) @@ -19,177 +10,176 @@ CO_OP_TRANSLATOR_METADATA: ### 🌐 다국어 지원 -#### GitHub Action을 통해 지원됨 (자동화 및 항상 최신 유지) +#### GitHub Action을 통한 지원 (자동화 및 항상 최신 상태 유지) -[Arabic](../ar/README.md) | [Bengali](../bn/README.md) | [Bulgarian](../bg/README.md) | [Burmese (Myanmar)](../my/README.md) | [Chinese (Simplified)](../zh/README.md) | [Chinese (Traditional, Hong Kong)](../hk/README.md) | [Chinese (Traditional, Macau)](../mo/README.md) | [Chinese (Traditional, Taiwan)](../tw/README.md) | [Croatian](../hr/README.md) | [Czech](../cs/README.md) | [Danish](../da/README.md) | [Dutch](../nl/README.md) | [Estonian](../et/README.md) | [Finnish](../fi/README.md) | [French](../fr/README.md) | [German](../de/README.md) | [Greek](../el/README.md) | [Hebrew](../he/README.md) | [Hindi](../hi/README.md) | [Hungarian](../hu/README.md) | [Indonesian](../id/README.md) | [Italian](../it/README.md) | [Japanese](../ja/README.md) | [Kannada](../kn/README.md) | [Korean](./README.md) | [Lithuanian](../lt/README.md) | [Malay](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepali](../ne/README.md) | [Nigerian Pidgin](../pcm/README.md) | [Norwegian](../no/README.md) | [Persian (Farsi)](../fa/README.md) | [Polish](../pl/README.md) | [Portuguese (Brazil)](../br/README.md) | [Portuguese (Portugal)](../pt/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Romanian](../ro/README.md) | [Russian](../ru/README.md) | [Serbian (Cyrillic)](../sr/README.md) | [Slovak](../sk/README.md) | [Slovenian](../sl/README.md) | [Spanish](../es/README.md) | [Swahili](../sw/README.md) | [Swedish](../sv/README.md) | [Tagalog (Filipino)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugu](../te/README.md) | [Thai](../th/README.md) | [Turkish](../tr/README.md) | [Ukrainian](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnamese](../vi/README.md) +[Arabic](../ar/README.md) | [Bengali](../bn/README.md) | [Bulgarian](../bg/README.md) | [Burmese (Myanmar)](../my/README.md) | [Chinese (Simplified)](../zh-CN/README.md) | [Chinese (Traditional, Hong Kong)](../zh-HK/README.md) | [Chinese (Traditional, Macau)](../zh-MO/README.md) | [Chinese (Traditional, Taiwan)](../zh-TW/README.md) | [Croatian](../hr/README.md) | [Czech](../cs/README.md) | [Danish](../da/README.md) | [Dutch](../nl/README.md) | [Estonian](../et/README.md) | [Finnish](../fi/README.md) | [French](../fr/README.md) | [German](../de/README.md) | [Greek](../el/README.md) | [Hebrew](../he/README.md) | [Hindi](../hi/README.md) | [Hungarian](../hu/README.md) | [Indonesian](../id/README.md) | [Italian](../it/README.md) | [Japanese](../ja/README.md) | [Kannada](../kn/README.md) | [Korean](./README.md) | [Lithuanian](../lt/README.md) | [Malay](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepali](../ne/README.md) | [Nigerian Pidgin](../pcm/README.md) | [Norwegian](../no/README.md) | [Persian (Farsi)](../fa/README.md) | [Polish](../pl/README.md) | [Portuguese (Brazil)](../pt-BR/README.md) | [Portuguese (Portugal)](../pt-PT/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Romanian](../ro/README.md) | [Russian](../ru/README.md) | [Serbian (Cyrillic)](../sr/README.md) | [Slovak](../sk/README.md) | [Slovenian](../sl/README.md) | [Spanish](../es/README.md) | [Swahili](../sw/README.md) | [Swedish](../sv/README.md) | [Tagalog (Filipino)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugu](../te/README.md) | [Thai](../th/README.md) | [Turkish](../tr/README.md) | [Ukrainian](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnamese](../vi/README.md) -> **로컬에 클론하기를 선호하시나요?** +> **로컬에서 복제하는 것을 선호하시나요?** -> 이 저장소에는 50개 이상의 언어 번역이 포함되어 있어 다운로드 크기가 크게 증가합니다. 번역 없이 클론하려면 스파스 체크아웃 기능을 사용하세요: +> 이 저장소에는 50개 이상의 언어 번역본이 포함되어 있어 다운로드 크기가 크게 늘어납니다. 번역 없이 복제하려면 sparse checkout을 사용하세요: > ```bash > git clone --filter=blob:none --sparse https://github.com/microsoft/ML-For-Beginners.git > cd ML-For-Beginners > git sparse-checkout set --no-cone '/*' '!translations' '!translated_images' > ``` -> 이렇게 하면 더 빠른 다운로드로 코스를 완료하는 데 필요한 모든 것을 얻을 수 있습니다. +> 이렇게 하면 훨씬 빠른 다운로드로 수업을 완료하는 데 필요한 모든 것을 얻을 수 있습니다. #### 커뮤니티에 참여하세요 [![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -우리는 현재 Discord에서 AI와 함께 배우기 시리즈를 진행 중이며, 2025년 9월 18일부터 30일까지 [Learn with AI Series](https://aka.ms/learnwithai/discord)에서 더 배우고 참여할 수 있습니다. 이 기간 동안 GitHub Copilot을 데이터 과학에 활용하는 팁과 요령을 얻을 수 있습니다. +우리는 Discord에서 AI와 함께 배우는 시리즈를 진행 중입니다. 2025년 9월 18일부터 30일까지 [Learn with AI Series](https://aka.ms/learnwithai/discord)에서 자세히 알아보고 함께하세요. GitHub Copilot을 데이터 과학에 활용하는 팁과 요령을 얻을 수 있습니다. -![Learn with AI series](../../../../translated_images/ko/3.9b58fd8d6c373c20.webp) +![Learn with AI series](../../translated_images/ko/3.9b58fd8d6c373c20.webp) -# 초보자를 위한 머신 러닝 - 커리큘럼 +# 초보자를 위한 머신러닝 - 커리큘럼 -> 🌍 세계 여러 문화와 함께 머신 러닝을 탐험하며 세계 여행을 떠나봅시다 🌍 +> 🌍 세계 문화를 통해 머신러닝을 탐험하며 세계 여행을 떠나보세요 🌍 -Microsoft의 클라우드 옹호자들은 12주, 26강의 커리큘럼인 **머신 러닝** 강좌를 기쁘게 제공합니다. 이 커리큘럼에서는 주로 Scikit-learn 라이브러리를 사용하여 흔히 말하는 **고전 머신 러닝**을 배우게 되며, 딥러닝은 [AI for Beginners 커리큘럼](https://aka.ms/ai4beginners)에서 다룹니다. 이 강의는 ['Data Science for Beginners' 커리큘럼](https://aka.ms/ds4beginners)과 함께 활용하면 좋습니다. +Microsoft의 클라우드 옹호자들이 제공하는 12주, 26강의 커리큘럼입니다. 이 커리큘럼에서는 주로 Scikit-learn 라이브러리를 사용하며 [AI for Beginners' curriculum](https://aka.ms/ai4beginners)에 포함된 딥러닝을 제외한, 종종 '클래식 머신러닝'이라 불리는 머신러닝에 대해 배웁니다. 또한, ['Data Science for Beginners' curriculum](https://aka.ms/ds4beginners)과 함께 학습할 수 있습니다. -세계 여러 나라의 데이터에 이 고전적 기술을 적용하며 우리와 함께 여행하세요. 각 강의는 강의 전후 퀴즈, 작성된 강의 안내, 솔루션, 과제 등을 포함합니다. 프로젝트 기반 교수법을 통해 학습하면서 동시에 제작하는 방식을 채택하여 새로운 기술을 효과적으로 습득할 수 있습니다. +전 세계 여러 지역의 데이터를 클래식 머신러닝 기법에 적용하며 여행하듯 배우세요. 각각의 강의는 강의 전후 퀴즈, 강의 완료 지침, 해답, 과제 등을 포함합니다. 프로젝트 기반 교육법은 실제 구축하면서 학습하도록 하여 새 기술이 잘 기억되도록 합니다. -**✍️ 진심으로 감사드립니다, 저자 분들께** Jen Looper, Stephen Howell, Francesca Lazzeri, Tomomi Imura, Cassie Breviu, Dmitry Soshnikov, Chris Noring, Anirban Mukherjee, Ornella Altunyan, Ruth Yakubu, Amy Boyd +**✍️ 진심으로 감사드립니다 - 저자분들** Jen Looper, Stephen Howell, Francesca Lazzeri, Tomomi Imura, Cassie Breviu, Dmitry Soshnikov, Chris Noring, Anirban Mukherjee, Ornella Altunyan, Ruth Yakubu, Amy Boyd -**🎨 그리고 일러스트레이터 분들께도 감사합니다** Tomomi Imura, Dasani Madipalli, Jen Looper +**🎨 감사드립니다 - 일러스트레이터분들** Tomomi Imura, Dasani Madipalli, Jen Looper -**🙏 특별 감사 인사 🙏 Microsoft 학생 앰배서더 저자, 검토자, 콘텐츠 기여자분들**, 특히 Rishit Dagli, Muhammad Sakib Khan Inan, Rohan Raj, Alexandru Petrescu, Abhishek Jaiswal, Nawrin Tabassum, Ioan Samuila, Snigdha Agarwal님께 +**🙏 특별한 감사 🙏 Microsoft 학생 앰배서더 저자, 검토자 및 콘텐츠 기여자분들** 특히 Rishit Dagli, Muhammad Sakib Khan Inan, Rohan Raj, Alexandru Petrescu, Abhishek Jaiswal, Nawrin Tabassum, Ioan Samuila, Snigdha Agarwal -**🤩 Microsoft 학생 앰배서더 Eric Wanjau, Jasleen Sondhi, Vidushi Gupta 님께 R 강의 관련 추가 감사!** +**🤩 추가 감사 - Microsoft 학생 앰배서더 Eric Wanjau, Jasleen Sondhi, Vidushi Gupta께서 진행한 R 강의!** # 시작하기 다음 단계를 따르세요: -1. **저장소 포크**: 이 페이지 우측 상단의 "Fork" 버튼을 클릭하세요. -2. **저장소 클론**: `git clone https://github.com/microsoft/ML-For-Beginners.git` +1. **리포지토리 포크**: 이 페이지 우측 상단의 "Fork" 버튼을 클릭합니다. +2. **리포지토리 복제**: `git clone https://github.com/microsoft/ML-For-Beginners.git` -> [이 코스의 모든 추가 리소스는 Microsoft Learn 모음에서 찾아보세요](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) +> [이 코스에 관한 모든 추가 자료는 Microsoft Learn 컬렉션에서 찾으실 수 있습니다](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) -> 🔧 **도움이 필요하신가요?** 설치, 설정 및 강의 실행 관련 일반적인 문제 해결책은 [문제 해결 가이드](TROUBLESHOOTING.md)를 참고하세요. +> 🔧 **도움이 필요하신가요?** 설치, 설정, 수업 실행 관련 일반 문제에 대한 해결책은 [문제 해결 설명서](TROUBLESHOOTING.md)를 확인하세요. +**[학생들](https://aka.ms/student-page)**, 이 커리큘럼을 사용하려면 전체 리포지토리를 자신의 GitHub 계정으로 포크하고 혼자 또는 그룹으로 연습문제를 완료하세요: -**[학생 여러분](https://aka.ms/student-page)**, 이 커리큘럼을 사용하려면 전체 저장소를 본인의 GitHub 계정으로 포크하여 혼자 또는 그룹과 함께 연습 문제를 완료하세요: +- 강의 전 퀴즈부터 시작하세요. +- 강의를 읽고 활동을 완성하며 각 지식 점검 부분에서 일시 중지하고 생각해 보세요. +- 해답 코드를 단순 실행하기보다는 내용을 이해하며 프로젝트를 제작해 보세요. 해답 코드는 각 프로젝트 별 수업의 `/solution` 폴더에 있습니다. +- 강의 후 퀴즈를 봅니다. +- 챌린지를 완료합니다. +- 과제를 완료합니다. +- 강의 그룹을 완료한 후 [토론 게시판](https://github.com/microsoft/ML-For-Beginners/discussions)에 방문해 적절한 PAT 루브릭을 작성하며 '소리 내어 학습'하세요. 'PAT'는 학습 진척 평가 도구로, 여러분이 직접 작성하여 더 깊이 학습하도록 돕습니다. 다른 PAT에도 반응하여 함께 배울 수 있습니다. -- 강의 전 퀴즈로 시작하세요. -- 강의를 읽고 활동을 완료하며 각 지식 점검에서 멈춰서 생각해보세요. -- 솔루션 코드를 실행하기보다는 강의를 이해하고 프로젝트를 만들어보려 시도하세요; 다만 해당 코드는 각 프로젝트 중심 강의 내 `/solution` 폴더에서 제공됩니다. -- 강의 후 퀴즈를 풀어보세요. -- 도전을 완료하세요. -- 과제를 완료하세요. -- 한 강의 그룹을 마친 후에는 [토론 게시판](https://github.com/microsoft/ML-For-Beginners/discussions)을 방문하여 적절한 PAT 루브릭을 작성하며 '소리 내어 배우기'를 실천하세요. 'PAT'는 학습 진척 평가 도구로 학습을 더 심화하는 루브릭입니다. 다른 PAT에도 반응할 수 있어 함께 배울 수 있습니다. +> 추가 학습을 원할 경우, 다음 [Microsoft Learn](https://docs.microsoft.com/en-us/users/jenlooper-2911/collections/k7o7tg1gp306q4?WT.mc_id=academic-77952-leestott) 모듈과 학습 경로를 추천합니다. -> 추가 학습을 위해 우리는 이 [Microsoft Learn](https://docs.microsoft.com/en-us/users/jenlooper-2911/collections/k7o7tg1gp306q4?WT.mc_id=academic-77952-leestott) 모듈과 학습 경로를 따른 것을 추천합니다. - -**교사분들께**, 이 커리큘럼을 활용하는 방법에 대한 [제안도 포함되어 있습니다](for-teachers.md). +**교사 분들**, 본 커리큘럼 활용에 대한 [권장 사항](for-teachers.md)을 포함하였습니다. --- -## 영상 강의 +## 비디오 강의 -몇몇 강의는 짧은 영상으로 제공됩니다. 해당 영상들은 강의 내 인라인으로 제공되거나, [Microsoft Developer YouTube 채널의 ML for Beginners 재생목록](https://aka.ms/ml-beginners-videos)에서 모두 확인할 수 있습니다. 아래 이미지를 클릭하세요. +일부 강의는 짧은 형식의 비디오로 제공됩니다. 모든 비디오는 강의 내 인라인 또는 [Microsoft Developer YouTube 채널의 ML for Beginners 재생목록](https://aka.ms/ml-beginners-videos)에서 이미지를 클릭하여 시청할 수 있습니다. -[![ML for beginners banner](../../../../translated_images/ko/ml-for-beginners-video-banner.63f694a100034bc6.webp)](https://aka.ms/ml-beginners-videos) +[![ML for beginners banner](../../translated_images/ko/ml-for-beginners-video-banner.63f694a100034bc6.webp)](https://aka.ms/ml-beginners-videos) --- ## 팀 소개 -[![프로모 영상](../../images/ml.gif)](https://youtu.be/Tj1XWrDSYJU) +[![Promo video](../../images/ml.gif)](https://youtu.be/Tj1XWrDSYJU) -**Gif 제작** [Mohit Jaisal](https://linkedin.com/in/mohitjaisal) +**GIF 제작** [Mohit Jaisal](https://linkedin.com/in/mohitjaisal) -> 🎥 위 이미지를 클릭하여 프로젝트와 제작진에 관한 영상을 보세요! +> 🎥 위 이미지를 클릭하면 프로젝트와 제작진에 관한 비디오를 볼 수 있습니다! --- -## 교수법 +## 교육 철학 -이 커리큘럼을 구축하면서 두 가지 교수학습 원칙을 선택했습니다: 실습 중심의 **프로젝트 기반 학습**과 **자주 퀴즈 보기**입니다. 또한 콘텐츠에 일관성을 주기 위해 공통 **주제**를 포함했습니다. +이 커리큘럼 개발 시 두 가지 교육 원칙을 채택했습니다: 실습 중심의 **프로젝트 기반** 교육과 **빈번한 퀴즈 포함**. 또한 통일성을 주기 위해 공통 **테마**를 적용했습니다. -내용이 프로젝트와 일치하게 함으로써 학생들이 더 몰입하고 개념의 이해도와 기억력을 높일 수 있습니다. 수업 전 낮은 부담의 퀴즈는 배우려는 의도를 세우게 하고, 수업 후 퀴즈는 개념의 유지력을 강화합니다. 이 커리큘럼은 유연하고 재미있게 설계되어 전체 또는 일부만 수강할 수 있습니다. 프로젝트는 작은 것부터 시작하여 12주 과정이 끝날 때쯤 점점 더 복잡해집니다. 또한 머신 러닝의 실제 적용 사례에 대한 후속 내용도 포함되어 있어 추가 학점 또는 토론 자료로 활용할 수 있습니다. +프로젝트와 내용이 일치하도록 함으로써 학생들이 수업에 몰입하고 개념을 더 잘 유지할 수 있도록 합니다. 수업 전 저위험 퀴즈는 학생들의 학습 의도를 세우고 수업 후 퀴즈는 개념의 유지력을 높입니다. 이 커리큘럼은 유연하고 재미있게 설계되어 전부 또는 일부만 수강할 수 있습니다. 프로젝트는 작게 시작해 12주 과정이 끝날 무렵 점점 더 복잡해집니다. 또한 실제 머신러닝 적용에 관한 후기 글이 포함되어 있어 추가 학점이나 토론 소재로 사용할 수 있습니다. -> [행동 강령](CODE_OF_CONDUCT.md), [기여 가이드](CONTRIBUTING.md), [번역 안내](TRANSLATIONS.md), [문제 해결 가이드](TROUBLESHOOTING.md)를 참고하세요. 여러분의 건설적인 피드백을 환영합니다! +> [행동 강령](CODE_OF_CONDUCT.md), [기여 지침](CONTRIBUTING.md), [번역 안내](TRANSLATIONS.md), [문제 해결](TROUBLESHOOTING.md) 가이드를 확인하세요. 건설적인 피드백을 환영합니다! -## 각 강의 포함 내용 +## 각 강의는 다음을 포함합니다 - 선택적 스케치노트 -- 선택적 보조 영상 -- 영상 강의 (일부 강의만) -- [강의 전 준비 퀴즈](https://ff-quizzes.netlify.app/en/ml/) -- 강의 작성본 -- 프로젝트 기반 강의에서는 단계별 프로젝트 제작 가이드 +- 선택적 보조 비디오 +- 비디오 강의(일부 강의만) +- [강의 전 워밍업 퀴즈](https://ff-quizzes.netlify.app/en/ml/) +- 서면 강의 +- 프로젝트 기반 강의의 경우, 프로젝트 구축 단계별 안내서 - 지식 점검 -- 도전 과제 -- 보충 읽기 자료 +- 챌린지 +- 보조 읽을거리 - 과제 - [강의 후 퀴즈](https://ff-quizzes.netlify.app/en/ml/) -> **언어에 대한 참고 사항**: 이 강의들은 주로 Python으로 작성되었지만, 많은 강의가 R로도 제공됩니다. R 강의를 완료하려면 `/solution` 폴더에서 R 강의를 찾아보세요. R 강의는 .rmd 확장자를 갖는 **R 마크다운** 파일로, 이는 R 또는 다른 언어의 코드 청크와 `YAML 헤더`(PDF 등 출력 형식을 지정하는)를 Markdown 문서에 포함한 형식입니다. 따라서 코드를 작성, 출력, 설명 등의 내용을 Markdown에 함께 기록할 수 있어 데이터 사이언스를 위한 훌륭한 저작 도구가 됩니다. 또한 R 마크다운 문서는 PDF, HTML, Word 등으로 렌더링할 수 있습니다. -> **퀴즈에 관한 참고**: 모든 퀴즈는 [퀴즈 앱 폴더](../../quiz-app)에 포함되어 있으며, 총 52개의 퀴즈 각각 3개의 질문으로 구성되어 있습니다. 이들은 강의 내에서 연결되어 있지만, 퀴즈 앱은 로컬에서 실행할 수 있습니다. 로컬 호스팅 또는 Azure에 배포하는 방법은 `quiz-app` 폴더의 지침을 따르세요. - -| 강의 번호 | 주제 | 강의 분류 | 학습 목표 | 연결된 강의 | 저자 | -| :-------: | :------------------------------------------------------------: | :--------------------------------------------: | ------------------------------------------------------------------------------------------------------------------------------ | :------------------------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------: | -| 01 | 머신러닝 소개 | [소개](1-Introduction/README.md) | 머신러닝의 기본 개념 학습 | [강의](1-Introduction/1-intro-to-ML/README.md) | Muhammad | -| 02 | 머신러닝의 역사 | [소개](1-Introduction/README.md) | 이 분야의 역사를 학습 | [강의](1-Introduction/2-history-of-ML/README.md) | Jen and Amy | -| 03 | 공정성과 머신러닝 | [소개](1-Introduction/README.md) | ML 모델을 구축하고 적용할 때 학생들이 고려해야 할 공정성에 관한 중요한 철학적 문제는 무엇인가? | [강의](1-Introduction/3-fairness/README.md) | Tomomi | -| 04 | 머신러닝 기법 | [소개](1-Introduction/README.md) | ML 연구자들이 ML 모델을 구축하기 위해 사용하는 기법은 무엇인가? | [강의](1-Introduction/4-techniques-of-ML/README.md) | Chris and Jen | -| 05 | 회귀 소개 | [회귀](2-Regression/README.md) | 회귀 모델을 위한 Python과 Scikit-learn 시작 | [Python](2-Regression/1-Tools/README.md) • [R](../../2-Regression/1-Tools/solution/R/lesson_1.html) | Jen • Eric Wanjau | -| 06 | 북미 호박 가격 🎃 | [회귀](2-Regression/README.md) | ML을 준비하는 데이터 시각화 및 정제 | [Python](2-Regression/2-Data/README.md) • [R](../../2-Regression/2-Data/solution/R/lesson_2.html) | Jen • Eric Wanjau | -| 07 | 북미 호박 가격 🎃 | [회귀](2-Regression/README.md) | 선형 및 다항 회귀 모델 구축 | [Python](2-Regression/3-Linear/README.md) • [R](../../2-Regression/3-Linear/solution/R/lesson_3.html) | Jen and Dmitry • Eric Wanjau | -| 08 | 북미 호박 가격 🎃 | [회귀](2-Regression/README.md) | 로지스틱 회귀 모델 구축 | [Python](2-Regression/4-Logistic/README.md) • [R](../../2-Regression/4-Logistic/solution/R/lesson_4.html) | Jen • Eric Wanjau | -| 09 | 웹 앱 🔌 | [웹 앱](3-Web-App/README.md) | 훈련된 모델을 사용할 웹 앱 구축 | [Python](3-Web-App/1-Web-App/README.md) | Jen | -| 10 | 분류 소개 | [분류](4-Classification/README.md) | 데이터 정제, 준비 및 시각화; 분류 소개 | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | Jen and Cassie • Eric Wanjau | -| 11 | 아시아 및 인도 음식 맛보기 🍜 | [분류](4-Classification/README.md) | 분류기 소개 | [Python](4-Classification/2-Classifiers-1/README.md) • [R](../../4-Classification/2-Classifiers-1/solution/R/lesson_11.html) | Jen and Cassie • Eric Wanjau | -| 12 | 아시아 및 인도 음식 맛보기 🍜 | [분류](4-Classification/README.md) | 더 많은 분류기 | [Python](4-Classification/3-Classifiers-2/README.md) • [R](../../4-Classification/3-Classifiers-2/solution/R/lesson_12.html) | Jen and Cassie • Eric Wanjau | -| 13 | 아시아 및 인도 음식 맛보기 🍜 | [분류](4-Classification/README.md) | 모델을 사용한 추천 웹 앱 구축 | [Python](4-Classification/4-Applied/README.md) | Jen | -| 14 | 군집화 소개 | [군집화](5-Clustering/README.md) | 데이터 정제, 준비 및 시각화; 군집화 소개 | [Python](5-Clustering/1-Visualize/README.md) • [R](../../5-Clustering/1-Visualize/solution/R/lesson_14.html) | Jen • Eric Wanjau | -| 15 | 나이지리아 음악 취향 탐색 🎧 | [군집화](5-Clustering/README.md) | K-평균 군집화 방법 탐색 | [Python](5-Clustering/2-K-Means/README.md) • [R](../../5-Clustering/2-K-Means/solution/R/lesson_15.html) | Jen • Eric Wanjau | -| 16 | 자연어 처리 소개 ☕️ | [자연어 처리](6-NLP/README.md) | 간단한 봇 제작으로 NLP 기초 학습 | [Python](6-NLP/1-Introduction-to-NLP/README.md) | Stephen | -| 17 | 일반적인 NLP 작업 ☕️ | [자연어 처리](6-NLP/README.md) | 언어 구조 처리 시 필요한 일반 작업 이해로 NLP 지식 심화 | [Python](6-NLP/2-Tasks/README.md) | Stephen | -| 18 | 번역 및 감정 분석 ♥️ | [자연어 처리](6-NLP/README.md) | Jane Austen을 이용한 번역 및 감정 분석 | [Python](6-NLP/3-Translation-Sentiment/README.md) | Stephen | -| 19 | 유럽의 낭만적인 호텔들 ♥️ | [자연어 처리](6-NLP/README.md) | 호텔 리뷰를 통한 감정 분석 1 | [Python](6-NLP/4-Hotel-Reviews-1/README.md) | Stephen | -| 20 | 유럽의 낭만적인 호텔들 ♥️ | [자연어 처리](6-NLP/README.md) | 호텔 리뷰를 통한 감정 분석 2 | [Python](6-NLP/5-Hotel-Reviews-2/README.md) | Stephen | -| 21 | 시계열 예측 소개 | [시계열](7-TimeSeries/README.md) | 시계열 예측 소개 | [Python](7-TimeSeries/1-Introduction/README.md) | Francesca | -| 22 | ⚡️ 세계 전력 사용량 ⚡️ - ARIMA로 시계열 예측 | [시계열](7-TimeSeries/README.md) | ARIMA를 이용한 시계열 예측 | [Python](7-TimeSeries/2-ARIMA/README.md) | Francesca | -| 23 | ⚡️ 세계 전력 사용량 ⚡️ - SVR로 시계열 예측 | [시계열](7-TimeSeries/README.md) | 서포트 벡터 회귀를 이용한 시계열 예측 | [Python](7-TimeSeries/3-SVR/README.md) | Anirban | -| 24 | 강화학습 소개 | [강화학습](8-Reinforcement/README.md) | Q-러닝을 이용한 강화학습 소개 | [Python](8-Reinforcement/1-QLearning/README.md) | Dmitry | -| 25 | 피터가 늑대를 피하도록 도와주세요! 🐺 | [강화학습](8-Reinforcement/README.md) | 강화학습 체육관 | [Python](8-Reinforcement/2-Gym/README.md) | Dmitry | -| 맺음말 | 실제 사례 기반 ML 시나리오 및 응용 | [실전 ML](9-Real-World/README.md) | 고전 ML의 흥미롭고 깨우치는 실제 응용 | [강의](9-Real-World/1-Applications/README.md) | 팀 | -| 맺음말 | RAI 대시보드를 이용한 ML 모델 디버깅 | [실전 ML](9-Real-World/README.md) | 책임 있는 AI 대시보드 구성요소를 활용한 머신러닝 모델 디버깅 | [강의](9-Real-World/2-Debugging-ML-Models/README.md) | Ruth Yakubu | - -> [본 과정의 모든 추가 자료를 Microsoft Learn 컬렉션에서 확인하세요](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) - -## 오프라인 접근 - -[Docsify](https://docsify.js.org/#/)를 사용하여 이 문서를 오프라인에서 실행할 수 있습니다. 이 저장소를 포크하고, 로컬 머신에 [Docsify를 설치](https://docsify.js.org/#/quickstart)한 후, 이 저장소의 루트 폴더에서 `docsify serve`를 입력하세요. 웹 사이트가 로컬호스트의 3000번 포트에서 제공됩니다: `localhost:3000`. +> **언어 관련 참고:** 이 강의들은 주로 Python으로 작성되었지만 많은 강의가 R 언어로도 제공됩니다. R 강의를 완료하려면 `/solution` 폴더에서 R 강의를 찾으세요. 이 파일은 .rmd 확장자를 가지며, 이는 `코드 청크`(R 또는 기타 언어의)와 `YAML 헤더`(출력 포맷 PDF 등 지정)를 포함하는 **R Markdown** 파일입니다. R Markdown은 코드, 출력, 생각을 Markdown 문서 내에 기록하여 결합할 수 있는 우수한 데이터 과학 작성 프레임워크입니다. 또한 PDF, HTML, Word 등 다양한 출력 포맷으로 렌더링할 수 있습니다. +> **퀴즈에 대한 참고 사항**: 모든 퀴즈는 [Quiz App 폴더](../../quiz-app)에 포함되어 있으며, 총 52개의 퀴즈가 각 3개의 질문으로 구성되어 있습니다. 이들은 강의 내에서 링크되어 있지만 퀴즈 앱은 로컬에서 실행할 수 있습니다; 로컬 호스팅 또는 Azure에 배포하는 방법은 `quiz-app` 폴더의 지침을 따르십시오. + +| 강의 번호 | 주제 | 강의 그룹 | 학습 목표 | 연결된 강의 | 저자 | +| :-------: | :------------------------------------------------------------: | :----------------------------------------------: | ------------------------------------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------: | +| 01 | 머신러닝 소개 | [소개](1-Introduction/README.md) | 머신러닝의 기본 개념을 학습합니다 | [강의](1-Introduction/1-intro-to-ML/README.md) | Muhammad | +| 02 | 머신러닝의 역사 | [소개](1-Introduction/README.md) | 이 분야의 역사에 대해 학습합니다 | [강의](1-Introduction/2-history-of-ML/README.md) | Jen and Amy | +| 03 | 공정성과 머신러닝 | [소개](1-Introduction/README.md) | 학생들이 ML 모델을 구축하고 적용할 때 고려해야 할 중요한 철학적 공정성 문제 | [강의](1-Introduction/3-fairness/README.md) | Tomomi | +| 04 | 머신러닝 기법 | [소개](1-Introduction/README.md) | ML 연구자가 모델을 구축할 때 사용하는 기법을 학습합니다 | [강의](1-Introduction/4-techniques-of-ML/README.md) | Chris and Jen | +| 05 | 회귀 소개 | [회귀](2-Regression/README.md) | 회귀 모델을 위한 Python과 Scikit-learn 시작 | [Python](2-Regression/1-Tools/README.md) • [R](../../2-Regression/1-Tools/solution/R/lesson_1.html) | Jen • Eric Wanjau | +| 06 | 북미 호박 가격 🎃 | [회귀](2-Regression/README.md) | ML 준비를 위한 데이터 시각화 및 정리 | [Python](2-Regression/2-Data/README.md) • [R](../../2-Regression/2-Data/solution/R/lesson_2.html) | Jen • Eric Wanjau | +| 07 | 북미 호박 가격 🎃 | [회귀](2-Regression/README.md) | 선형 및 다항 회귀 모델 구축 | [Python](2-Regression/3-Linear/README.md) • [R](../../2-Regression/3-Linear/solution/R/lesson_3.html) | Jen and Dmitry • Eric Wanjau | +| 08 | 북미 호박 가격 🎃 | [회귀](2-Regression/README.md) | 로지스틱 회귀 모델 구축 | [Python](2-Regression/4-Logistic/README.md) • [R](../../2-Regression/4-Logistic/solution/R/lesson_4.html) | Jen • Eric Wanjau | +| 09 | 웹 앱 🔌 | [웹 앱](3-Web-App/README.md) | 훈련된 모델을 활용하는 웹 앱 구축 | [Python](3-Web-App/1-Web-App/README.md) | Jen | +| 10 | 분류 소개 | [분류](4-Classification/README.md) | 데이터 정리, 준비, 시각화; 분류 소개 | [Python](4-Classification/1-Introduction/README.md) • [R](../../4-Classification/1-Introduction/solution/R/lesson_10.html) | Jen and Cassie • Eric Wanjau | +| 11 | 맛있는 아시아 및 인도 요리 🍜 | [분류](4-Classification/README.md) | 분류기 소개 | [Python](4-Classification/2-Classifiers-1/README.md) • [R](../../4-Classification/2-Classifiers-1/solution/R/lesson_11.html) | Jen and Cassie • Eric Wanjau | +| 12 | 맛있는 아시아 및 인도 요리 🍜 | [분류](4-Classification/README.md) | 더 많은 분류기 | [Python](4-Classification/3-Classifiers-2/README.md) • [R](../../4-Classification/3-Classifiers-2/solution/R/lesson_12.html) | Jen and Cassie • Eric Wanjau | +| 13 | 맛있는 아시아 및 인도 요리 🍜 | [분류](4-Classification/README.md) | 모델을 사용한 추천 웹 앱 구축 | [Python](4-Classification/4-Applied/README.md) | Jen | +| 14 | 클러스터링 소개 | [클러스터링](5-Clustering/README.md) | 데이터 정리, 준비, 시각화; 클러스터링 소개 | [Python](5-Clustering/1-Visualize/README.md) • [R](../../5-Clustering/1-Visualize/solution/R/lesson_14.html) | Jen • Eric Wanjau | +| 15 | 나이지리아 음악 취향 탐색 🎧 | [클러스터링](5-Clustering/README.md) | K-평균 클러스터링 방법 탐구 | [Python](5-Clustering/2-K-Means/README.md) • [R](../../5-Clustering/2-K-Means/solution/R/lesson_15.html) | Jen • Eric Wanjau | +| 16 | 자연어 처리 소개 ☕️ | [자연어 처리](6-NLP/README.md) | 간단한 봇을 만들어 NLP 기본 개념 학습 | [Python](6-NLP/1-Introduction-to-NLP/README.md) | Stephen | +| 17 | 일반 NLP 작업 ☕️ | [자연어 처리](6-NLP/README.md) | 언어 구조를 다룰 때 필요한 일반적인 NLP 작업을 이해하며 지식 심화 | [Python](6-NLP/2-Tasks/README.md) | Stephen | +| 18 | 번역 및 감정 분석 ♥️ | [자연어 처리](6-NLP/README.md) | Jane Austen 텍스트로 번역과 감정 분석 | [Python](6-NLP/3-Translation-Sentiment/README.md) | Stephen | +| 19 | 유럽의 로맨틱 호텔 ♥️ | [자연어 처리](6-NLP/README.md) | 호텔 리뷰를 통한 감정 분석 1 | [Python](6-NLP/4-Hotel-Reviews-1/README.md) | Stephen | +| 20 | 유럽의 로맨틱 호텔 ♥️ | [자연어 처리](6-NLP/README.md) | 호텔 리뷰를 통한 감정 분석 2 | [Python](6-NLP/5-Hotel-Reviews-2/README.md) | Stephen | +| 21 | 시계열 예측 소개 | [시계열](7-TimeSeries/README.md) | 시계열 예측 소개 | [Python](7-TimeSeries/1-Introduction/README.md) | Francesca | +| 22 | ⚡️ 세계 전력 사용 ⚡️ - ARIMA 시계열 예측 | [시계열](7-TimeSeries/README.md) | ARIMA를 이용한 시계열 예측 | [Python](7-TimeSeries/2-ARIMA/README.md) | Francesca | +| 23 | ⚡️ 세계 전력 사용 ⚡️ - SVR 시계열 예측 | [시계열](7-TimeSeries/README.md) | 서포트 벡터 회귀를 이용한 시계열 예측 | [Python](7-TimeSeries/3-SVR/README.md) | Anirban | +| 24 | 강화 학습 소개 | [강화 학습](8-Reinforcement/README.md) | Q-러닝을 이용한 강화 학습 소개 | [Python](8-Reinforcement/1-QLearning/README.md) | Dmitry | +| 25 | Peter가 늑대를 피하도록 돕기! 🐺 | [강화 학습](8-Reinforcement/README.md) | 강화 학습 Gym | [Python](8-Reinforcement/2-Gym/README.md) | Dmitry | +| 후기글 | 실제 ML 시나리오 및 응용 | [야생의 ML](9-Real-World/README.md) | 고전적인 ML의 흥미롭고 실질적인 실제 적용 사례 | [강의](9-Real-World/1-Applications/README.md) | 팀 | +| 후기글 | RAI 대시보드를 활용한 ML 모델 디버깅 | [야생의 ML](9-Real-World/README.md) | 책임 있는 AI 대시보드 컴포넌트를 사용한 머신러닝 모델 디버깅 | [강의](9-Real-World/2-Debugging-ML-Models/README.md) | Ruth Yakubu | + +> [이 과정의 모든 추가 자료는 Microsoft Learn 컬렉션에서 확인하세요](https://learn.microsoft.com/en-us/collections/qrqzamz1nn2wx3?WT.mc_id=academic-77952-bethanycheum) + +## 오프라인 액세스 + +이 문서를 오프라인에서 실행하려면 [Docsify](https://docsify.js.org/#/)를 사용하세요. 이 저장소를 포크하고, 로컬 머신에 [Docsify 설치](https://docsify.js.org/#/quickstart) 후 이 저장소의 루트 폴더에서 `docsify serve`를 입력하세요. 웹사이트는 로컬호스트의 3000번 포트에서 서빙됩니다: `localhost:3000`. ## PDF -강의 계획서 PDF는 [여기](https://microsoft.github.io/ML-For-Beginners/pdf/readme.pdf)에서 확인할 수 있습니다. +링크가 포함된 커리큘럼 PDF는 [여기](https://microsoft.github.io/ML-For-Beginners/pdf/readme.pdf)에서 확인하세요. -## 🎒 기타 강의 +## 🎒 다른 강좌 -저희 팀은 다른 강의들도 제작하고 있습니다! 확인해보세요: +우리 팀은 다른 강좌도 제작합니다! 확인해보세요: ### LangChain -[![초보자를 위한 LangChain4j](https://img.shields.io/badge/LangChain4j%20for%20Beginners-22C55E?style=for-the-badge&&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchain4j-for-beginners) -[![초보자를 위한 LangChain.js](https://img.shields.io/badge/LangChain.js%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin) +[![LangChain4j for Beginners](https://img.shields.io/badge/LangChain4j%20for%20Beginners-22C55E?style=for-the-badge&&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchain4j-for-beginners) +[![LangChain.js for Beginners](https://img.shields.io/badge/LangChain.js%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin) --- -### Azure / Edge / MCP / 에이전트 -[![초보자를 위한 AZD](https://img.shields.io/badge/AZD%20for%20Beginners-0078D4?style=for-the-badge&labelColor=E5E7EB&color=0078D4)](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst) -[![초보자를 위한 Edge AI](https://img.shields.io/badge/Edge%20AI%20for%20Beginners-00B8E4?style=for-the-badge&labelColor=E5E7EB&color=00B8E4)](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst) -[![초보자를 위한 MCP](https://img.shields.io/badge/MCP%20for%20Beginners-009688?style=for-the-badge&labelColor=E5E7EB&color=009688)](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst) -[![초보자를 위한 AI 에이전트](https://img.shields.io/badge/AI%20Agents%20for%20Beginners-00C49A?style=for-the-badge&labelColor=E5E7EB&color=00C49A)](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst) +### Azure / Edge / MCP / Agents +[![AZD for Beginners](https://img.shields.io/badge/AZD%20for%20Beginners-0078D4?style=for-the-badge&labelColor=E5E7EB&color=0078D4)](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst) +[![Edge AI for Beginners](https://img.shields.io/badge/Edge%20AI%20for%20Beginners-00B8E4?style=for-the-badge&labelColor=E5E7EB&color=00B8E4)](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst) +[![MCP for Beginners](https://img.shields.io/badge/MCP%20for%20Beginners-009688?style=for-the-badge&labelColor=E5E7EB&color=009688)](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst) +[![AI Agents for Beginners](https://img.shields.io/badge/AI%20Agents%20for%20Beginners-00C49A?style=for-the-badge&labelColor=E5E7EB&color=00C49A)](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst) --- -### 생성형 AI 시리즈 +### 생성 AI 시리즈 [![초보자를 위한 생성 AI](https://img.shields.io/badge/Generative%20AI%20for%20Beginners-8B5CF6?style=for-the-badge&labelColor=E5E7EB&color=8B5CF6)](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst) [![생성 AI (.NET)](https://img.shields.io/badge/Generative%20AI%20(.NET)-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst) [![생성 AI (Java)](https://img.shields.io/badge/Generative%20AI%20(Java)-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst) @@ -209,24 +199,24 @@ Microsoft의 클라우드 옹호자들은 12주, 26강의 커리큘럼인 **머 --- ### 코파일럿 시리즈 -[![AI 페어 프로그래밍용 코파일럿](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) +[![AI 페어 프로그래밍을 위한 코파일럿](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) [![C#/.NET용 코파일럿](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst) [![코파일럿 어드벤처](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) ## 도움 받기 -AI 앱 구축 중 막히거나 질문이 있다면, MCP에 대해 토론하는 동료 학습자 및 경험 많은 개발자들과 함께 하세요. 질문이 환영받고 지식이 자유롭게 공유되는 지원 커뮤니티입니다. +AI 앱 개발 중에 막히거나 질문이 있는 경우 MCP 커뮤니티에 참여해 보세요. 질문이 환영받고 지식이 자유롭게 공유되는 지원적인 커뮤니티입니다. [![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -제품 피드백이나 빌드 중 오류가 있다면 다음을 방문하세요: +제품 피드백이나 개발 중 오류가 발생하면 다음을 방문하세요: -[![Microsoft Foundry 개발자 포럼](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum) +[![Microsoft Foundry Developer Forum](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum) --- **면책 조항**: -이 문서는 AI 번역 서비스 [Co-op Translator](https://github.com/Azure/co-op-translator)를 사용하여 번역되었습니다. 정확성을 위해 최선을 다하고 있으나, 자동 번역에는 오류나 부정확성이 포함될 수 있음을 양지해 주시기 바랍니다. 원문은 해당 언어의 원본 문서를 권위 있는 자료로 간주해야 합니다. 중요한 정보의 경우, 전문적인 사람 번역을 권장합니다. 본 번역 사용으로 인한 오해나 잘못된 해석에 대해서는 당사는 책임을 지지 않습니다. +이 문서는 AI 번역 서비스 [Co-op Translator](https://github.com/Azure/co-op-translator)를 사용하여 번역되었습니다. 정확성을 위해 노력하였으나, 자동 번역에는 오류나 부정확성이 포함될 수 있음을 유의해 주시기 바랍니다. 원문 문서는 권위 있는 출처로 간주되어야 합니다. 중요한 정보의 경우 전문적인 인간 번역을 권장합니다. 이 번역의 사용으로 인해 발생하는 오해나 잘못된 해석에 대해 당사는 책임을 지지 않습니다. \ No newline at end of file diff --git a/translations/ko/SECURITY.md b/translations/ko/SECURITY.md index 0b7f2dd59..4e22eb599 100644 --- a/translations/ko/SECURITY.md +++ b/translations/ko/SECURITY.md @@ -1,12 +1,3 @@ - ## 보안 Microsoft는 소프트웨어 제품과 서비스의 보안을 매우 중요하게 생각하며, 여기에는 [Microsoft](https://github.com/Microsoft), [Azure](https://github.com/Azure), [DotNet](https://github.com/dotnet), [AspNet](https://github.com/aspnet), [Xamarin](https://github.com/xamarin), 그리고 [Microsoft의 GitHub 조직들](https://opensource.microsoft.com/)에서 관리하는 모든 소스 코드 저장소가 포함됩니다. diff --git a/translations/ko/SUPPORT.md b/translations/ko/SUPPORT.md index 11107d96a..d436ed978 100644 --- a/translations/ko/SUPPORT.md +++ b/translations/ko/SUPPORT.md @@ -1,12 +1,3 @@ - # 지원 ## 문제 신고 및 도움 받는 방법 diff --git a/translations/ko/TROUBLESHOOTING.md b/translations/ko/TROUBLESHOOTING.md index 1293581da..0f09262f4 100644 --- a/translations/ko/TROUBLESHOOTING.md +++ b/translations/ko/TROUBLESHOOTING.md @@ -1,12 +1,3 @@ - # 문제 해결 가이드 이 가이드는 Machine Learning for Beginners 커리큘럼을 사용할 때 발생하는 일반적인 문제를 해결하는 데 도움을 줍니다. 여기서 해결책을 찾지 못한 경우, [Discord Discussions](https://aka.ms/foundry/discord) 또는 [문제 등록](https://github.com/microsoft/ML-For-Beginners/issues)을 확인하세요. diff --git a/translations/ko/docs/_sidebar.md b/translations/ko/docs/_sidebar.md index 8454549a6..264b74f98 100644 --- a/translations/ko/docs/_sidebar.md +++ b/translations/ko/docs/_sidebar.md @@ -1,12 +1,3 @@ - - 소개 - [머신 러닝 소개](../1-Introduction/1-intro-to-ML/README.md) - [머신 러닝의 역사](../1-Introduction/2-history-of-ML/README.md) diff --git a/translations/ko/for-teachers.md b/translations/ko/for-teachers.md index a2ef1a08e..1509a274b 100644 --- a/translations/ko/for-teachers.md +++ b/translations/ko/for-teachers.md @@ -1,12 +1,3 @@ - ## 교육자를 위한 안내 이 커리큘럼을 교실에서 사용하고 싶으신가요? 자유롭게 활용하세요! diff --git a/translations/ko/quiz-app/README.md b/translations/ko/quiz-app/README.md index 4d0fb5475..56a89f820 100644 --- a/translations/ko/quiz-app/README.md +++ b/translations/ko/quiz-app/README.md @@ -1,12 +1,3 @@ - # 퀴즈 이 퀴즈는 https://aka.ms/ml-beginners에서 제공하는 ML 커리큘럼의 강의 전후 퀴즈입니다. diff --git a/translations/ko/sketchnotes/LICENSE.md b/translations/ko/sketchnotes/LICENSE.md index 9c515d485..370ad18f2 100644 --- a/translations/ko/sketchnotes/LICENSE.md +++ b/translations/ko/sketchnotes/LICENSE.md @@ -1,12 +1,3 @@ - Attribution-ShareAlike 4.0 국제 ======================================================================= diff --git a/translations/ko/sketchnotes/README.md b/translations/ko/sketchnotes/README.md index f9dc63f6f..e144aaa9d 100644 --- a/translations/ko/sketchnotes/README.md +++ b/translations/ko/sketchnotes/README.md @@ -1,12 +1,3 @@ - 모든 커리큘럼의 스케치노트를 여기에서 다운로드할 수 있습니다. 🖨 고해상도로 인쇄하려면 TIFF 버전을 [이 저장소](https://github.com/girliemac/a-picture-is-worth-a-1000-words/tree/main/ml/tiff)에서 이용할 수 있습니다.