diff --git a/1-Introduction/1-intro-to-ML/translations/README.zh-cn.md b/1-Introduction/1-intro-to-ML/translations/README.zh-cn.md index e919ff02..de5d22b0 100644 --- a/1-Introduction/1-intro-to-ML/translations/README.zh-cn.md +++ b/1-Introduction/1-intro-to-ML/translations/README.zh-cn.md @@ -4,7 +4,7 @@ > 🎥 点击上面的图片观看讨论机器学习、人工智能和深度学习之间区别的视频。 -## [课前测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/1/) +## [课前测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/1/?loc=zh) ### 介绍 @@ -96,7 +96,7 @@ 在纸上或使用 [Excalidraw](https://excalidraw.com/) 等在线应用程序绘制草图，了解你对 AI、ML、深度学习和数据科学之间差异的理解。添加一些关于这些技术擅长解决的问题的想法。 -## [阅读后测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/2/) +## [阅读后测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/2/?loc=zh) ## 复习与自学 diff --git a/1-Introduction/2-history-of-ML/translations/README.zh-cn.md b/1-Introduction/2-history-of-ML/translations/README.zh-cn.md index ddd2430d..16c495cb 100644 --- a/1-Introduction/2-history-of-ML/translations/README.zh-cn.md +++ b/1-Introduction/2-history-of-ML/translations/README.zh-cn.md @@ -3,7 +3,7 @@ ![机器学习历史概述](../../../sketchnotes/ml-history.png) > 作者 [Tomomi Imura](https://www.twitter.com/girlie_mac) -## [课前测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/3/) +## [课前测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/3/?loc=zh) 在本课中，我们将走过机器学习和人工智能历史上的主要里程碑。 @@ -101,7 +101,7 @@ Alan Turing，一个真正杰出的人，[在 2019 年被公众投票选出](htt 深入了解这些历史时刻之一，并更多地了解它们背后的人。这里有许多引人入胜的人物，没有一项科学发现是在文化真空中创造出来的。你发现了什么？ -## [课后测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/4/) +## [课后测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/4/?loc=zh) ## 复习与自学 diff --git a/1-Introduction/3-fairness/translations/README.zh-cn.md b/1-Introduction/3-fairness/translations/README.zh-cn.md index 03f30d4d..1e10a6e0 100644 --- a/1-Introduction/3-fairness/translations/README.zh-cn.md +++ b/1-Introduction/3-fairness/translations/README.zh-cn.md @@ -3,7 +3,7 @@ ![机器学习中的公平性概述](../../../sketchnotes/ml-fairness.png) > 作者 [Tomomi Imura](https://www.twitter.com/girlie_mac) -## [课前测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/5/) +## [课前测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/5/?loc=zh) ## 介绍 @@ -186,7 +186,7 @@ 想想现实生活中的场景，在模型构建和使用中明显存在不公平。我们还应该考虑什么？ -## [课后测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/6/) +## [课后测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/6/?loc=zh) ## 复习与自学 在本课中，你学习了机器学习中公平和不公平概念的一些基础知识。 diff --git a/1-Introduction/4-techniques-of-ML/translations/README.zh-cn.md b/1-Introduction/4-techniques-of-ML/translations/README.zh-cn.md index d135b596..0a89c4dc 100644 --- a/1-Introduction/4-techniques-of-ML/translations/README.zh-cn.md +++ b/1-Introduction/4-techniques-of-ML/translations/README.zh-cn.md @@ -6,7 +6,7 @@ - 在高层次上理解支持机器学习的过程。 - 探索基本概念，例如“模型”、“预测”和“训练数据”。 -## [课前测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/7/) +## [课前测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/7/?loc=zh) ## 介绍 在较高的层次上，创建机器学习（ML）过程的工艺包括许多步骤： @@ -101,7 +101,7 @@ 画一个流程图，反映ML的步骤。在这个过程中，你认为自己现在在哪里？你预测你在哪里会遇到困难？什么对你来说很容易？ -## [阅读后测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/8/) +## [阅读后测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/8/?loc=zh) ## 复习与自学 diff --git a/2-Regression/1-Tools/translations/README.zh-cn.md b/2-Regression/1-Tools/translations/README.zh-cn.md index d7e65684..8502272c 100644 --- a/2-Regression/1-Tools/translations/README.zh-cn.md +++ b/2-Regression/1-Tools/translations/README.zh-cn.md @@ -4,7 +4,7 @@ > 作者 [Tomomi Imura](https://www.twitter.com/girlie_mac) -## [课前测](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/9/) +## [课前测](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/9/?loc=zh) ## 介绍 在这四节课中，你将了解如何构建回归模型。我们将很快讨论这些是什么。但在你做任何事情之前，请确保你有合适的工具来开始这个过程！ @@ -194,7 +194,7 @@ Scikit-learn 使构建模型和评估它们的使用变得简单。它主要侧 从这个数据集中绘制一个不同的变量。提示：编辑这一行：`X = X[:, np.newaxis, 2]`。鉴于此数据集的目标，你能够发现糖尿病作为一种疾病的进展情况吗？ -## [课后测](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/10/) +## [课后测](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/10/?loc=zh) ## 复习与自学 diff --git a/2-Regression/2-Data/translations/README.zh-cn.md b/2-Regression/2-Data/translations/README.zh-cn.md index 215f7411..f91445ac 100644 --- a/2-Regression/2-Data/translations/README.zh-cn.md +++ b/2-Regression/2-Data/translations/README.zh-cn.md @@ -3,7 +3,7 @@ ![数据可视化信息图](../images/data-visualization.png) > 作者 [Dasani Madipalli](https://twitter.com/dasani_decoded) -## [课前测](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/11/) +## [课前测](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/11/?loc=zh) ## 介绍 @@ -192,7 +192,7 @@ 探索 Matplotlib 提供的不同类型的可视化。哪种类型最适合回归问题？ -## [课后测](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/12/) +## [课后测](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/12/?loc=zh) ## 复习与自学 diff --git a/2-Regression/3-Linear/translations/README.zh-cn.md b/2-Regression/3-Linear/translations/README.zh-cn.md index da5e02ad..6ade5de1 100644 --- a/2-Regression/3-Linear/translations/README.zh-cn.md +++ b/2-Regression/3-Linear/translations/README.zh-cn.md @@ -3,7 +3,7 @@ ![线性与多项式回归信息图](../images/linear-polynomial.png) > 作者 [Dasani Madipalli](https://twitter.com/dasani_decoded) -## [课前测](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/13/) +## [课前测](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/13/?loc=zh) ### 介绍 @@ -330,7 +330,7 @@ Scikit-learn 包含一个用于构建多项式回归模型的有用 API - `make_ 在此 notebook 中测试几个不同的变量，以查看相关性与模型准确性的对应关系。 -## [课后测](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/14/) +## [课后测](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/14/?loc=zh) ## 复习与自学 diff --git a/2-Regression/4-Logistic/translations/README.zh-cn.md b/2-Regression/4-Logistic/translations/README.zh-cn.md index f1aa240f..a1bc46c4 100644 --- a/2-Regression/4-Logistic/translations/README.zh-cn.md +++ b/2-Regression/4-Logistic/translations/README.zh-cn.md @@ -3,7 +3,7 @@ ![逻辑与线性回归信息图](../images/logistic-linear.png) > 作者 [Dasani Madipalli](https://twitter.com/dasani_decoded) -## [课前测](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/15/) +## [课前测](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/15/?loc=zh) ## 介绍 @@ -289,7 +289,7 @@ print(auc) 关于逻辑回归，还有很多东西需要解开！但最好的学习方法是实验。找到适合此类分析的数据集并用它构建模型。你学到了什么？小贴士：尝试 [Kaggle](https://kaggle.com) 获取有趣的数据集。 -## [课后测](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/16/) +## [课后测](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/16/?loc=zh) ## 复习与自学 diff --git a/3-Web-App/1-Web-App/translations/README.zh-cn.md b/3-Web-App/1-Web-App/translations/README.zh-cn.md index 1ed88068..27bdf7cd 100644 --- a/3-Web-App/1-Web-App/translations/README.zh-cn.md +++ b/3-Web-App/1-Web-App/translations/README.zh-cn.md @@ -11,7 +11,7 @@ 为此，你需要使用 Flask 构建一个 web 应用程序。 -## [课前测](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/17/) +## [课前测](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/17/?loc=zh) ## 构建应用程序 @@ -334,7 +334,7 @@ print(model.predict([[50,44,-12]])) 你可以在 Flask 应用程序中训练模型，而不是在 notebook 上工作并将模型导入 Flask 应用程序！尝试在 notebook 中转换 Python 代码，可能是在清除数据之后，从应用程序中的一个名为 `train` 的路径训练模型。采用这种方法的利弊是什么？ -## [课后测](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/18/) +## [课后测](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/18/?loc=zh) ## 复习与自学 diff --git a/4-Classification/1-Introduction/translations/README.zh-cn.md b/4-Classification/1-Introduction/translations/README.zh-cn.md index 9c762e84..e089d77d 100644 --- a/4-Classification/1-Introduction/translations/README.zh-cn.md +++ b/4-Classification/1-Introduction/translations/README.zh-cn.md @@ -19,7 +19,7 @@ 分类方法采用多种算法来确定其他可以用来确定一个数据点的标签或类别的方法。让我们来研究一下这个数据集，看看我们能否通过观察菜肴的原料来确定它的源头。 -## [课程前的小问题](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/19/) +## [课程前的小问题](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/19/?loc=zh) 分类是机器学习研究者和数据科学家使用的一种基本方法。从基本的二元分类（这是不是一份垃圾邮件？）到复杂的图片分类和使用计算机视觉的分割技术，它都是将数据分类并提出相关问题的有效工具。 @@ -280,7 +280,7 @@ Scikit-learn 项目提供多种对数据进行分类的算法，你需要根据 本项目的全部课程含有很多有趣的数据集。 探索一下 `data` 文件夹，看看这里面有没有适合二元分类、多元分类算法的数据集，再想一下你对这些数据集有没有什么想问的问题。 -## [课后练习](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/20/) +## [课后练习](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/20/?loc=zh) ## 回顾 & 自学 diff --git a/4-Classification/2-Classifiers-1/translations/README.zh-cn.md b/4-Classification/2-Classifiers-1/translations/README.zh-cn.md index 4add5d4f..70264731 100644 --- a/4-Classification/2-Classifiers-1/translations/README.zh-cn.md +++ b/4-Classification/2-Classifiers-1/translations/README.zh-cn.md @@ -4,7 +4,7 @@ 你将使用此数据集和各种分类器，_根据一组配料预测这是哪一国家的美食_。在此过程中，你将学到更多用来权衡分类任务算法的方法 -## [课前测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/21/) +## [课前测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/21/?loc=zh) # 准备工作 @@ -230,7 +230,7 @@ X_train, X_test, y_train, y_test = train_test_split(cuisines_feature_df, cuisine 在本课程中，你使用了清洗后的数据建立了一个机器学习的模型，这个模型能够根据输入的一系列的配料来预测菜品来自于哪个国家。请再花点时间阅读一下 Scikit-learn 所提供的关于可以用来分类数据的其他方法的资料。此外，你也可以深入研究一下“solver”的概念并尝试一下理解其背后的原理。 -## [课后测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/22/) +## [课后测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/22/?loc=zh) ## 回顾与自学 diff --git a/4-Classification/3-Classifiers-2/translations/README.zh-cn.md b/4-Classification/3-Classifiers-2/translations/README.zh-cn.md index 51cf64cf..91f703ab 100644 --- a/4-Classification/3-Classifiers-2/translations/README.zh-cn.md +++ b/4-Classification/3-Classifiers-2/translations/README.zh-cn.md @@ -2,7 +2,7 @@ 在第二节课程中，您将探索更多方法来对数值数据进行分类。您还将了解选择不同的分类器所带来的结果。 -## [课前测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/23/) +## [课前测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/23/?loc=zh) ### 先决条件 @@ -224,7 +224,7 @@ weighted avg 0.73 0.72 0.72 1199 这些技术方法每个都有很多能够让您微调的参数。研究每一个的默认参数，并思考调整这些参数对模型质量有何意义。 -## [课后测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/24/) +## [课后测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/24/?loc=zh) ## 回顾与自学 diff --git a/5-Clustering/1-Visualize/translations/README.zh-cn.md b/5-Clustering/1-Visualize/translations/README.zh-cn.md index 5b699c62..58a1ba12 100644 --- a/5-Clustering/1-Visualize/translations/README.zh-cn.md +++ b/5-Clustering/1-Visualize/translations/README.zh-cn.md @@ -6,7 +6,7 @@ > 🎥 点击上面的图片观看视频。当您通过聚类学习机器学习时，请欣赏一些尼日利亚舞厅曲目 - 这是 2014 年 PSquare 上高度评价的歌曲。 -## [课前测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/27/) +## [课前测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/27/?loc=zh) ### 介绍 @@ -326,7 +326,7 @@ 聚类试图解决什么样的问题？ -## [课后测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/28/) +## [课后测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/28/?loc=zh) ## 复习与自学 diff --git a/5-Clustering/2-K-Means/translations/README.zh-cn.md b/5-Clustering/2-K-Means/translations/README.zh-cn.md index 3a9fba1c..3e62dae7 100644 --- a/5-Clustering/2-K-Means/translations/README.zh-cn.md +++ b/5-Clustering/2-K-Means/translations/README.zh-cn.md @@ -4,7 +4,7 @@ > 🎥 单击上图观看视频：Andrew Ng 解释聚类 -## [课前测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/29/) +## [课前测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/29/?loc=zh) 在本课中，您将学习如何使用 Scikit-learn 和您之前导入的尼日利亚音乐数据集创建聚类。我们将介绍 K-Means 聚类 的基础知识。请记住，正如您在上一课中学到的，使用聚类的方法有很多种，您使用的方法取决于您的数据。我们将尝试 K-Means，因为它是最常见的聚类技术。让我们开始吧！ @@ -239,7 +239,7 @@ K-Means 聚类过程[分三步执行](https://scikit-learn.org/stable/modules/cl 提示：尝试缩放您的数据。笔记本中的注释代码添加了标准缩放，使数据列在范围方面更加相似。您会发现，当轮廓分数下降时，肘部图中的“扭结”变得平滑。这是因为不缩放数据可以让方差较小的数据承载更多的权重。在[这里](https://stats.stackexchange.com/questions/21222/are-mean-normalization-and-feature-scaling-needed-for-k-means-clustering/21226#21226)阅读更多关于这个问题的[信息](https://stats.stackexchange.com/questions/21222/are-mean-normalization-and-feature-scaling-needed-for-k-means-clustering/21226#21226)。 -## [课后测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/30/) +## [课后测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/30/?loc=zh) ## 复习与自学 diff --git a/6-NLP/1-Introduction-to-NLP/translations/README.zh-cn.md b/6-NLP/1-Introduction-to-NLP/translations/README.zh-cn.md index 97428b49..93181b1f 100644 --- a/6-NLP/1-Introduction-to-NLP/translations/README.zh-cn.md +++ b/6-NLP/1-Introduction-to-NLP/translations/README.zh-cn.md @@ -1,7 +1,7 @@ # 自然语言处理介绍 这节课讲解了 *自然语言处理* 的简要历史和重要概念，*自然语言处理*是计算语言学的一个子领域。 -## [课前测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/31/) +## [课前测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/31/?loc=zh) ## 介绍 众所周知，自然语言处理（Natural Language Processing, NLP）是机器学习在生产软件中应用最广泛的领域之一。 @@ -147,7 +147,7 @@ 在下一课中，您将了解解析自然语言和机器学习的许多其他方法。 -## [课后测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/32/) +## [课后测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/32/?loc=zh) ## 复习与自学 diff --git a/8-Reinforcement/1-QLearning/translations/README.zh-cn.md b/8-Reinforcement/1-QLearning/translations/README.zh-cn.md index e047c895..196f4ee0 100644 --- a/8-Reinforcement/1-QLearning/translations/README.zh-cn.md +++ b/8-Reinforcement/1-QLearning/translations/README.zh-cn.md @@ -11,7 +11,7 @@ > 🎥 点击上图观看 Dmitry 讨论强化学习 -## [课前测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/45/) +## [课前测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/45/?loc=zh) ## 先决条件和设置 @@ -315,6 +315,6 @@ print_statistics(qpolicy) 总的来说，重要的是要记住学习过程的成功和质量在很大程度上取决于参数，例如学习率、学习率衰减和折扣因子。这些通常称为**超参数**，以区别于我们在训练期间优化的**参数**（例如，Q-Table 系数）。寻找最佳超参数值的过程称为**超参数优化**，它值得一个单独的话题来介绍。 -## [课后测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/46/) +## [课后测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/46/?loc=zh) ## 作业[一个更真实的世界](assignment.zh-cn.md) diff --git a/8-Reinforcement/2-Gym/translations/README.zh-cn.md b/8-Reinforcement/2-Gym/translations/README.zh-cn.md index 9ff984d6..9873cffa 100644 --- a/8-Reinforcement/2-Gym/translations/README.zh-cn.md +++ b/8-Reinforcement/2-Gym/translations/README.zh-cn.md @@ -3,7 +3,7 @@ 我们在上一课中一直在解决的问题可能看起来像一个玩具问题，并不真正适用于现实生活场景。事实并非如此，因为许多现实世界的问题也有这种情况——包括下国际象棋或围棋。它们很相似，因为我们也有一个具有给定规则和**离散状态**的板。 https://white-water-09ec41f0f.azurestaticapps.net/ -## [课前测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/47/) +## [课前测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/47/?loc=zh) ## 介绍 @@ -330,7 +330,7 @@ env.close() > **任务 4**：这里我们不是在每一步选择最佳动作，而是用相应的概率分布进行采样。始终选择具有最高 Q-Table 值的最佳动作是否更有意义？这可以通过使用 `np.argmax` 函数找出对应于较高 Q-Table 值的动作编号来完成。实施这个策略，看看它是否能改善平衡。 -## [课后测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/48/) +## [课后测验](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/48/?loc=zh) ## 作业：[训练山地车](assignment.zh-cn.md) diff --git a/quiz-app/src/App.vue b/quiz-app/src/App.vue index e2a958e5..10e019fc 100644 --- a/quiz-app/src/App.vue +++ b/quiz-app/src/App.vue @@ -11,6 +11,7 @@ +
diff --git a/quiz-app/src/assets/translations/index.js b/quiz-app/src/assets/translations/index.js index 031e6671..39bf5192 100644 --- a/quiz-app/src/assets/translations/index.js +++ b/quiz-app/src/assets/translations/index.js @@ -6,6 +6,7 @@ import ja from './ja.json'; import it from './it.json'; import ptbr from './ptbr.json'; import es from './es.json'; +import zh from './zh.json'; //export const defaultLocale = 'en'; @@ -16,7 +17,8 @@ const messages = { ja: ja[0], it: it[0], ptbr: ptbr[0], - es: es[0] + es: es[0], + zh: zh[0] }; export default messages; diff --git a/quiz-app/src/assets/translations/zh.json b/quiz-app/src/assets/translations/zh.json new file mode 100644 index 00000000..5f455ee1 --- /dev/null +++ b/quiz-app/src/assets/translations/zh.json @@ -0,0 +1,2929 @@ +[ + { + "title": "机器学习初学者：测验", + "complete": "恭喜你完成了测验！", + "error": "抱歉，请再试一次", + "quizzes": [ + { + "id": 1, + "title": "机器学习简介：课前测验", + "quiz": [ + { + "questionText": "机器学习的应用无处不在", + "answerOptions": [ + { + "answerText": "真", + "isCorrect": "true" + }, + { + "answerText": "假", + "isCorrect": "false" + } + ] + }, + { + "questionText": "传统机器学习和深度学习的技术差异是什么？", + "answerOptions": [ + { + "answerText": "传统机器学习首先被发明", + "isCorrect": "false" + }, + { + "answerText": "使用神经网络", + "isCorrect": "true" + }, + { + "answerText": "深度学习在机器人中使用", + "isCorrect": "false" + } + ] + }, + { + "questionText": "为什么企业想要使用机器学习策略？", + "answerOptions": [ + { + "answerText": "自动化解决多维问题", + "isCorrect": "false" + }, + { + "answerText": "根据客户类型自定义购物体验", + "isCorrect": "false" + }, + { + "answerText": "以上两个都是", + "isCorrect": "true" + } + ] + } + ] + }, + { + "id": 2, + "title": "机器学习简介：课后测验", + "quiz": [ + { + "questionText": "机器学习算法旨在模拟", + "answerOptions": [ + { + "answerText": "智能机器", + "isCorrect": "false" + }, + { + "answerText": "人脑", + "isCorrect": "true" + }, + { + "answerText": "猩猩", + "isCorrect": "false" + } + ] + }, + { + "questionText": "传统机器学习技术的一个例子是什么？", + "answerOptions": [ + { + "answerText": "自然语言处理", + "isCorrect": "true" + }, + { + "answerText": "深度学习", + "isCorrect": "false" + }, + { + "answerText": "神经网络", + "isCorrect": "false" + } + ] + }, + { + "questionText": "为什么每个人都应该学习机器学习的基础知识？", + "answerOptions": [ + { + "answerText": "学习机器学习有趣且适用于每个人", + "isCorrect": "false" + }, + { + "answerText": "机器学习策略正在许多行业和领域中使用", + "isCorrect": "false" + }, + { + "answerText": "以上两者都是", + "isCorrect": "true" + } + ] + }, + { + "id": 3, + "title": "机器学习的历史：课前测验", + "quiz": [ + { + "questionText": "大约在什么时候出现了“人工智能”一词？", + "answerOptions": [ + { + "answerText": "1980年代", + "isCorrect": "false" + }, + { + "answerText": "1950年代", + "isCorrect": "true" + }, + { + "answerText": "1930年代", + "isCorrect": "false" + } + ] + }, + { + "questionText": "谁是机器学习的早期先驱之一？", + "answerOptions": [ + { + "answerText": "艾伦·图灵", + "isCorrect": "true" + }, + { + "answerText": "比尔·盖茨", + "isCorrect": "false" + }, + { + "answerText": "Shakey 机器人", + "isCorrect": "false" + } + ] + }, + { + "questionText": "导致 1970年代AI发展减缓的原因之一是什么？", + "answerOptions": [ + { + "answerText": "计算能力有限", + "isCorrect": "true" + }, + { + "answerText": "缺乏熟练的工程师", + "isCorrect": "false" + }, + { + "answerText": "国家之间的冲突", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 4, + "title": "机器学习的历史：课后测验", + "quiz": [ + { + "questionText": "什么是“杂乱”的AI系统的一个例子？", + "answerOptions": [ + { + "answerText": "ELIZA", + "isCorrect": "true" + }, + { + "answerText": "HACKML", + "isCorrect": "false" + }, + { + "answerText": "SSYSTEM", + "isCorrect": "false" + } + ] + } + ] + }, + { + "questionText": "在“黄金年代”期间开发的技术的一个例子是什么？", + "answerOptions": [ + { + "answerText": "块世界", + "isCorrect": "true" + }, + { + "answerText": "Jibo", + "isCorrect": "false" + }, + { + "answerText": "机器狗", + "isCorrect": "false" + } + ] + }, + { + "questionText": "哪个事件对人工智能领域的创立和扩展具有基础性意义？", + "answerOptions": [ + { + "answerText": "图灵测试", + "isCorrect": "false" + }, + { + "answerText": "达特茅斯夏季研究计划", + "isCorrect": "true" + }, + { + "answerText": "AI寒冬", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 5, + "title": "公平与机器学习：课前测验", + "quiz": [ + { + "questionText": "机器学习中的不公平可以是", + "answerOptions": [ + { + "answerText": "有意的", + "isCorrect": "false" + }, + { + "answerText": "无意的", + "isCorrect": "false" + }, + { + "answerText": "以上两者都有可能", + "isCorrect": "true" + } + ] + }, + { + "questionText": "ML中的“不公平”一词意味着：", + "answerOptions": [ + { + "answerText": "对一群人造成的伤害", + "isCorrect": "true" + }, + { + "answerText": "对一个人的伤害", + "isCorrect": "false" + }, + { + "answerText": "对大多数人造成的伤害", + "isCorrect": "false" + } + ] + }, + { + "questionText": "五种主要的危害类型包括", + "answerOptions": [ + { + "answerText": "分配、服务质量、刻板印象、贬低和过度或不足的代表性", + "isCorrect": "true" + }, + { + "answerText": "重定位、服务质量、刻板印象、贬低和过度或不足的代表性", + "isCorrect": "false" + }, + { + "answerText": "分配、服务质量、立体声效果、贬低和过度或不足的代表性", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 6, + "title": "公平性和机器学习：课后测验", + "quiz": [ + { + "questionText": "模型中的不公平可能由以下原因导致", + "answerOptions": [ + { + "answerText": "过度依赖历史数据", + "isCorrect": "true" + }, + { + "answerText": "历史数据过少", + "isCorrect": "false" + }, + { + "answerText": "过于紧密地与历史数据一致", + "isCorrect": "false" + } + ] + }, + { + "questionText": "为减少不公平，可以", + "answerOptions": [ + { + "answerText": "确定伤害和受影响的群体", + "isCorrect": "false" + }, + { + "answerText": "定义公平度量", + "isCorrect": "false" + }, + { + "answerText": "以上两者", + "isCorrect": "true" + } + ] + }, + { + "questionText": "Fairlearn是一个包，可以", + "answerOptions": [ + { + "answerText": "使用公平性和性能度量比较多个模型", + "isCorrect": "true" + }, + { + "answerText": "为您的需求选择最佳模型", + "isCorrect": "false" + }, + { + "answerText": "帮助您决定什么是公平的，什么是不公平的", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 7, + "title": "工具和技术：课前测验", + "quiz": [ + { + "questionText": "建立模型时，您应该：", + "answerOptions": [ + { + "answerText": "准备数据，然后训练模型", + "isCorrect": "true" + }, + { + "answerText": "选择训练方法，然后准备数据", + "isCorrect": "false" + }, + { + "answerText": "调整参数，然后训练模型", + "isCorrect": "false" + } + ] + }, + { + "questionText": "您的数据的 ___ 将影响您的ML模型的质量", + "answerOptions": [ + { + "answerText": "数量", + "isCorrect": "false" + }, + { + "answerText": "形状", + "isCorrect": "false" + }, + { + "answerText": "以上两者", + "isCorrect": "true" + } + ] + }, + { + "questionText": "特征变量是指：", + "answerOptions": [ + { + "answerText": "数据的质量", + "isCorrect": "false" + }, + { + "answerText": "数据的可测属性", + "isCorrect": "true" + }, + { + "answerText": "数据的一行", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 8, + "title": "工具和技术：课后测验", + "quiz": [ + { + "questionText": "为什么要可视化数据？", + "answerOptions": [ + { + "answerText": "可以发现异常值", + "isCorrect": "false" + }, + { + "answerText": "可以发现偏差的潜在原因", + "isCorrect": "false" + }, + { + "answerText": "以上两个都是", + "isCorrect": "true" + } + ] + }, + { + "questionText": "将数据分成哪些部分？", + "answerOptions": [ + { + "answerText": "训练集和图灵集", + "isCorrect": "false" + }, + { + "answerText": "训练集和测试集", + "isCorrect": "true" + }, + { + "answerText": "验证集和评估集", + "isCorrect": "false" + } + ] + }, + { + "questionText": "在各种机器学习库中启动训练过程的常见命令是什么？", + "answerOptions": [ + { + "answerText": "model.travel", + "isCorrect": "false" + }, + { + "answerText": "model.train", + "isCorrect": "false" + }, + { + "answerText": "model.fit", + "isCorrect": "true" + } + ] + } + ] + }, + { + "id": 9, + "title": "回归入门：课前测验", + "quiz": [ + { + "questionText": "以下哪个变量是数字变量？", + "answerOptions": [ + { + "answerText": "身高", + "isCorrect": "true" + }, + { + "answerText": "性别", + "isCorrect": "false" + }, + { + "answerText": "头发颜色", + "isCorrect": "false" + } + ] + }, + { + "questionText": "以下哪个变量是分类变量？", + "answerOptions": [ + { + "answerText": "心率", + "isCorrect": "false" + }, + { + "answerText": "血型", + "isCorrect": "true" + }, + { + "answerText": "体重", + "isCorrect": "false" + } + ] + }, + { + "questionText": "以下哪个问题是基于回归分析的问题？", + "answerOptions": [ + { + "answerText": "预测学生的期末考试成绩", + "isCorrect": "true" + }, + { + "answerText": "预测一个人的血型", + "isCorrect": "false" + }, + { + "answerText": "预测一封电子邮件是否为垃圾邮件", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 10, + "title": "回归介绍：课后测验", + "quiz": [ + { + "questionText": "如果您的机器学习模型的训练准确率为95%，测试准确率为30%，那么它被称为什么类型的情况？", + "answerOptions": [ + { + "answerText": "过拟合", + "isCorrect": "true" + }, + { + "answerText": "欠拟合", + "isCorrect": "false" + }, + { + "answerText": "双重拟合", + "isCorrect": "false" + } + ] + }, + { + "questionText": "从一组特征中识别重要特征的过程被称为：", + "answerOptions": [ + { + "answerText": "特征提取", + "isCorrect": "false" + }, + { + "answerText": "特征降维", + "isCorrect": "false" + }, + { + "answerText": "特征选择", + "isCorrect": "true" + } + ] + }, + { + "questionText": "使用 Scikit Learn 的 'train_test_split()' 方法/函数将数据集按一定比例划分为训练集和测试集的过程被称为：", + "answerOptions": [ + { + "answerText": "交叉验证", + "isCorrect": "false" + }, + { + "answerText": "保持验证", + "isCorrect": "true" + }, + { + "answerText": "留一验证", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 11, + "title": "为回归分析准备和可视化数据：课前测验", + "quiz": [ + { + "questionText": "以下哪个Python模块用于绘制数据可视化？", + "answerOptions": [ + { + "answerText": "Numpy", + "isCorrect": "false" + }, + { + "answerText": "Scikit-learn", + "isCorrect": "false" + }, + { + "answerText": "Matplotlib", + "isCorrect": "true" + } + ] + }, + { + "questionText": "如果你想了解数据集数据点的分布或其他特征，那么应该执行：", + "answerOptions": [ + { + "answerText": "数据可视化", + "isCorrect": "true" + }, + { + "answerText": "数据预处理", + "isCorrect": "false" + }, + { + "answerText": "训练测试分离", + "isCorrect": "false" + } + ] + }, + { + "questionText": "以下哪个是机器学习项目中数据可视化步骤的一部分？", + "answerOptions": [ + { + "answerText": "结合某种机器学习算法", + "isCorrect": "false" + }, + { + "answerText": "使用不同的绘图方法创建数据的图形表示", + "isCorrect": "true" + }, + { + "answerText": "归一化数据集的值", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 12, + "title": "为回归准备和可视化数据：课后测验", + "quiz": [ + { + "questionText": "根据本课程，如果您想检查数据集中是否存在缺失值，哪些代码片段是正确的？假设数据集存储在名为“数据集”的变量中，该变量是一个Pandas DataFrame对象。", + "answerOptions": [ + { + "answerText": "dataset.isnull().sum()", + "isCorrect": "true" + }, + { + "answerText": "findMissing(dataset)", + "isCorrect": "false" + }, + { + "answerText": "sum(null(dataset))", + "isCorrect": "false" + } + ] + }, + { + "questionText": "当您想了解来自数据集的不同数据点组的分布时，哪些绘图方法很有用？", + "answerOptions": [ + { + "answerText": "散点图", + "isCorrect": "false" + }, + { + "answerText": "折线图", + "isCorrect": "false" + }, + { + "answerText": "条形图", + "isCorrect": "true" + } + ] + }, + { + "questionText": "数据可视化不能告诉您什么？", + "answerOptions": [ + { + "answerText": "数据点之间的关系", + "isCorrect": "false" + }, + { + "answerText": "数据集的来源", + "isCorrect": "true" + }, + { + "answerText": "数据集中异常值的存在", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 13, + "title": "线性和多项式回归：课前测验", + "quiz": [ + { + "questionText": "Matplotlib是一个", + "answerOptions": [ + { + "answerText": "绘图库", + "isCorrect": "false" + }, + { + "answerText": "数据可视化库", + "isCorrect": "true" + }, + { + "answerText": "借书库", + "isCorrect": "false" + } + ] + }, + { + "questionText": "线性回归使用以下哪种方式来绘制变量之间的关系？", + "answerOptions": [ + { + "answerText": "直线", + "isCorrect": "true" + }, + { + "answerText": "圆形", + "isCorrect": "false" + }, + { + "answerText": "曲线", + "isCorrect": "false" + } + ] + }, + { + "questionText": "一个好的线性回归模型具有___相关系数", + "answerOptions": [ + { + "answerText": "低", + "isCorrect": "false" + }, + { + "answerText": "高", + "isCorrect": "true" + }, + { + "answerText": "平坦", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 14, + "title": "线性和多项式回归: 课后测验", + "quiz": [ + { + "questionText": "如果你的数据是非线性的，请尝试使用___类型的回归", + "answerOptions": [ + { + "answerText": "线性回归", + "isCorrect": "false" + }, + { + "answerText": "球形回归", + "isCorrect": "false" + }, + { + "answerText": "多项式回归", + "isCorrect": "true" + } + ] + }, + { + "questionText": "这些都是回归方法的类型", + "answerOptions": [ + { + "answerText": "Falsestep、Ridge、Lasso和Elasticnet", + "isCorrect": "false" + }, + { + "answerText": "Stepwise、Ridge、Lasso和Elasticnet", + "isCorrect": "true" + }, + { + "answerText": "Stepwise、Ridge、Lariat和Elasticnet", + "isCorrect": "false" + } + ] + }, + { + "questionText": "最小二乘回归意味着围绕回归线的所有数据点都是:", + "answerOptions": [ + { + "answerText": "平方后减去", + "isCorrect": "false" + }, + { + "answerText": "乘以", + "isCorrect": "false" + }, + { + "answerText": "平方后加起来", + "isCorrect": "true" + } + ] + } + ] + }, + { + "id": 15, + "title": "逻辑回归：课前测验", + "quiz": [ + { + "questionText": "使用逻辑回归进行预测", + "answerOptions": [ + { + "answerText": "苹果是否成熟", + "isCorrect": "true" + }, + { + "answerText": "一个月内能售出多少票", + "isCorrect": "false" + }, + { + "answerText": "明天下午六点天空会变成什么颜色", + "isCorrect": "false" + } + ] + }, + { + "questionText": "逻辑回归的类型包括", + "answerOptions": [ + { + "answerText": "多项式和基数", + "isCorrect": "false" + }, + { + "answerText": "多项式和序数", + "isCorrect": "true" + }, + { + "answerText": "主要和序数", + "isCorrect": "false" + } + ] + }, + { + "questionText": "你的数据相关性较弱。使用最佳的回归类型是：", + "answerOptions": [ + { + "answerText": "逻辑回归", + "isCorrect": "true" + }, + { + "answerText": "线性回归", + "isCorrect": "false" + }, + { + "answerText": "基数回归", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 16, + "title": "逻辑回归：课后测验", + "quiz": [ + { + "questionText": "Seaborn 是一种", + "answerOptions": [ + { + "answerText": "数据可视化库", + "isCorrect": "true" + }, + { + "answerText": "地图库", + "isCorrect": "false" + }, + { + "answerText": "数学库", + "isCorrect": "false" + } + ] + }, + { + "questionText": "混淆矩阵也被称为:", + "answerOptions": [ + { + "answerText": "误差矩阵", + "isCorrect": "true" + }, + { + "answerText": "真值矩阵", + "isCorrect": "false" + }, + { + "answerText": "准确率矩阵", + "isCorrect": "false" + } + ] + }, + { + "questionText": "一个好的模型将会拥有:", + "answerOptions": [ + { + "answerText": "混淆矩阵中大量的假阳性和真阴性", + "isCorrect": "false" + }, + { + "answerText": "混淆矩阵中大量的真阳性和真阴性", + "isCorrect": "true" + }, + { + "answerText": "混淆矩阵中大量的真阳性和假阴性", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 17, + "title": "构建Web应用程序：课前测验", + "quiz": [ + { + "questionText": "ONNX 代表什么？", + "answerOptions": [ + { + "answerText": "超级神经网络交换", + "isCorrect": "false" + }, + { + "answerText": "开放神经网络交换", + "isCorrect": "true" + }, + { + "answerText": "输出神经网络交换", + "isCorrect": "false" + } + ] + }, + { + "questionText": "Flask 如何被其创建者定义？", + "answerOptions": [ + { + "answerText": "迷你框架", + "isCorrect": "false" + }, + { + "answerText": "大型框架", + "isCorrect": "false" + }, + { + "answerText": "微型框架", + "isCorrect": "true" + } + ] + }, + { + "questionText": "Python 的 Pickle 模块是用来做什么的？", + "answerOptions": [ + { + "answerText": "序列化 Python 对象", + "isCorrect": "false" + }, + { + "answerText": "反序列化 Python 对象", + "isCorrect": "false" + }, + { + "answerText": "序列化和反序列化 Python 对象", + "isCorrect": "true" + } + ] + } + ] + }, + { + "id": 18, + "title": "构建 Web 应用程序：课后测验", + "quiz": [ + { + "questionText": "我们可以使用哪些工具来使用 Python 在 Web 上托管预训练模型？", + "answerOptions": [ + { + "answerText": "Flask", + "isCorrect": "true" + }, + { + "answerText": "TensorFlow.js", + "isCorrect": "false" + }, + { + "answerText": "onnx.js", + "isCorrect": "false" + } + ] + }, + { + "questionText": "SaaS代表什么？", + "answerOptions": [ + { + "answerText": "作为服务的系统", + "isCorrect": "false" + }, + { + "answerText": "作为服务的软件", + "isCorrect": "true" + }, + { + "answerText": "作为服务的安全", + "isCorrect": "false" + } + ] + }, + { + "questionText": "Scikit-learn的LabelEncoder库是做什么的？", + "answerOptions": [ + { + "answerText": "按字母表顺序编码数据", + "isCorrect": "true" + }, + { + "answerText": "按数字顺序编码数据", + "isCorrect": "false" + }, + { + "answerText": "按顺序编码数据", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 19, + "title": "分类 1：课前测验", + "quiz": [ + { + "questionText": "分类是有监督学习的一种形式，与哪种技术有许多共同之处？", + "answerOptions": [ + { + "answerText": "时间序列", + "isCorrect": "false" + }, + { + "answerText": "回归技术", + "isCorrect": "true" + }, + { + "answerText": "自然语言处理", + "isCorrect": "false" + } + ] + }, + { + "questionText": "分类技术可以回答哪个问题？", + "answerOptions": [ + { + "answerText": "这个邮件是垃圾邮件吗？", + "isCorrect": "true" + }, + { + "answerText": "猪能飞吗？", + "isCorrect": "false" + }, + { + "answerText": "生命的意义是什么？", + "isCorrect": "false" + } + ] + }, + { + "questionText": "使用分类技术的第一步是什么？", + "answerOptions": [ + { + "answerText": "创建数据集的类别", + "isCorrect": "false" + }, + { + "answerText": "清理和平衡数据", + "isCorrect": "true" + }, + { + "answerText": "将数据点分配给组或结果", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 20, + "title": "分类 1: 课后测验", + "quiz": [ + { + "questionText": "什么是多类问题?", + "answerOptions": [ + { + "answerText": "将数据点分类为多个类别的任务", + "isCorrect": "false" + }, + { + "answerText": "将数据点分类为多个类别中的一个的任务", + "isCorrect": "true" + }, + { + "answerText": "以多种方式清理数据点的任务", + "isCorrect": "false" + } + ] + }, + { + "questionText": "清除经常出现或无用的数据对于帮助分类器解决问题非常重要。", + "answerOptions": [ + { + "answerText": "正确", + "isCorrect": "true" + }, + { + "answerText": "错误", + "isCorrect": "false" + } + ] + }, + { + "questionText": "平衡数据的最好原因是什么？", + "answerOptions": [ + { + "answerText": "不平衡的数据在可视化中看起来不好", + "isCorrect": "false" + }, + { + "answerText": "平衡数据能产生更好的结果，因为机器学习模型不会偏向一个类别", + "isCorrect": "true" + }, + { + "answerText": "平衡数据可以获得更多的数据点", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 21, + "title": "分类 2: 课前测验", + "quiz": [ + { + "questionText": "平衡、干净的数据可以产生最佳的分类结果", + "answerOptions": [ + { + "answerText": "正确", + "isCorrect": "true" + }, + { + "answerText": "错误", + "isCorrect": "false" + } + ] + }, + { + "questionText": "如何选择正确的分类器？", + "answerOptions": [ + { + "answerText": "了解哪种分类器最适合哪种情况", + "isCorrect": "false" + }, + { + "answerText": "经验性的猜测和检查", + "isCorrect": "false" + }, + { + "answerText": "以上两者", + "isCorrect": "true" + } + ] + }, + { + "questionText": "分类是一种", + "answerOptions": [ + { + "answerText": "自然语言处理（NLP）", + "isCorrect": "false" + }, + { + "answerText": "监督学习", + "isCorrect": "true" + }, + { + "answerText": "编程语言", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 22, + "title": "分类 2：课后测验", + "quiz": [ + { + "questionText": "什么是“求解器”？", + "answerOptions": [ + { + "answerText": "检查您的工作的人", + "isCorrect": "false" + }, + { + "answerText": "在优化问题中使用的算法", + "isCorrect": "true" + }, + { + "answerText": "机器学习技术", + "isCorrect": "false" + } + ] + }, + { + "questionText": "我们在本课程中使用了哪种分类器？", + "answerOptions": [ + { + "answerText": "逻辑回归", + "isCorrect": "true" + }, + { + "answerText": "决策树", + "isCorrect": "false" + }, + { + "answerText": "一对多多类", + "isCorrect": "false" + } + ] + }, + { + "questionText": "如何知道分类算法是否按预期工作？", + "answerOptions": [ + { + "answerText": "通过检查其预测的准确性", + "isCorrect": "true" + }, + { + "answerText": "通过与其他算法比较", + "isCorrect": "false" + }, + { + "answerText": "通过查看历史数据，了解此算法在解决类似问题方面的效果如何", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 23, + "title": "分类 3：课前测验", + "quiz": [ + { + "questionText": "尝试的一个好的初始分类器是:", + "answerOptions": [ + { + "answerText": "线性 SVC", + "isCorrect": "true" + }, + { + "answerText": "K-Means", + "isCorrect": "false" + }, + { + "answerText": "逻辑 SVC", + "isCorrect": "false" + } + ] + }, + { + "questionText": "正则化控制:", + "answerOptions": [ + { + "answerText": "参数的影响", + "isCorrect": "true" + }, + { + "answerText": "训练速度的影响", + "isCorrect": "false" + }, + { + "answerText": "异常值的影响", + "isCorrect": "false" + } + ] + }, + { + "questionText": "K-最近邻分类器可用于:", + "answerOptions": [ + { + "answerText": "监督学习", + "isCorrect": "false" + }, + { + "answerText": "无监督学习", + "isCorrect": "false" + }, + { + "answerText": "这两种情况都可以", + "isCorrect": "true" + } + ] + } + ] + }, + { + "id": 24, + "title": "分类3：课后测验", + "quiz": [ + { + "questionText": "支持向量分类器可用于", + "answerOptions": [ + { + "answerText": "分类", + "isCorrect": "false" + }, + { + "answerText": "回归", + "isCorrect": "false" + }, + { + "answerText": "以上都是", + "isCorrect": "true" + } + ] + }, + { + "questionText": "随机森林是一种___类型的分类器", + "answerOptions": [ + { + "answerText": "集成", + "isCorrect": "true" + }, + { + "answerText": "解散", + "isCorrect": "false" + }, + { + "answerText": "装配", + "isCorrect": "false" + } + ] + }, + { + "questionText": "Adaboost以___而著名：", + "answerOptions": [ + { + "answerText": "专注于错误分类项目的权重", + "isCorrect": "true" + }, + { + "answerText": "专注于异常值", + "isCorrect": "false" + }, + { + "answerText": "专注于不正确的数据", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 25, + "title": "分类4: 课前测验", + "quiz": [ + { + "questionText": "推荐系统可能会被用于", + "answerOptions": [ + { + "answerText": "推荐好餐厅", + "isCorrect": "false" + }, + { + "answerText": "推荐尝试的时尚服装", + "isCorrect": "false" + }, + { + "answerText": "以上都是", + "isCorrect": "true" + } + ] + }, + { + "questionText": "在Web应用中嵌入模型有助于它具备离线功能", + "answerOptions": [ + { + "answerText": "正确", + "isCorrect": "true" + }, + { + "answerText": "错误", + "isCorrect": "false" + } + ] + }, + { + "questionText": "Onnx Runtime可用于", + "answerOptions": [ + { + "answerText": "在 Web 应用中运行模型", + "isCorrect": "true" + }, + { + "answerText": "训练模型", + "isCorrect": "false" + }, + { + "answerText": "超参数调整", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 26, + "title": "分类 4：课后测验", + "quiz": [ + { + "questionText": "Netron应用程序可以帮助您：", + "answerOptions": [ + { + "answerText": "可视化数据", + "isCorrect": "false" + }, + { + "answerText": "可视化模型的结构", + "isCorrect": "true" + }, + { + "answerText": "测试您的 Web 应用程序", + "isCorrect": "false" + } + ] + }, + { + "questionText": "使用以下哪个工具将Scikit-learn 型转换为Onnx模型：", + "answerOptions": [ + { + "answerText": "sklearn-app", + "isCorrect": "false" + }, + { + "answerText": "sklearn-web", + "isCorrect": "false" + }, + { + "answerText": "sklearn-onnx", + "isCorrect": "true" + } + ] + }, + { + "questionText": "在Web应用程序中使用模型称为：", + "answerOptions": [ + { + "answerText": "推理", + "isCorrect": "true" + }, + { + "answerText": "干涉", + "isCorrect": "false" + }, + { + "answerText": "保险", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 27, + "title": "聚类介绍：课前测验", + "quiz": [ + { + "questionText": "聚类的一个实际例子是：", + "answerOptions": [ + { + "answerText": "摆餐具", + "isCorrect": "false" + }, + { + "answerText": "分类洗衣服", + "isCorrect": "true" + }, + { + "answerText": "购物", + "isCorrect": "false" + } + ] + }, + { + "questionText": "这些行业可以使用聚类技术：", + "answerOptions": [ + { + "answerText": "银行业", + "isCorrect": "false" + }, + { + "answerText": "电子商务", + "isCorrect": "false" + }, + { + "answerText": "以上两者都可以", + "isCorrect": "true" + } + ] + }, + { + "questionText": "聚类是一种：", + "answerOptions": [ + { + "answerText": "监督学习", + "isCorrect": "false" + }, + { + "answerText": "无监督学习", + "isCorrect": "true" + }, + { + "answerText": "强化学习", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 28, + "title": "聚类介绍：课后测验", + "quiz": [ + { + "questionText": "欧几里得几何沿着什么排列：", + "answerOptions": [ + { + "answerText": "平面", + "isCorrect": "true" + }, + { + "answerText": "曲线", + "isCorrect": "false" + }, + { + "answerText": "球体", + "isCorrect": "false" + } + ] + }, + { + "questionText": "你的聚类数据的密度与其什么有关：", + "answerOptions": [ + { + "answerText": "噪音", + "isCorrect": "true" + }, + { + "answerText": "深度", + "isCorrect": "false" + }, + { + "answerText": "有效性", + "isCorrect": "false" + } + ] + }, + { + "questionText": "最著名的聚类算法是：", + "answerOptions": [ + { + "answerText": "k-means", + "isCorrect": "true" + }, + { + "answerText": "k-middle", + "isCorrect": "false" + }, + { + "answerText": "k-mart", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 29, + "title": "K-Means聚类: 课前测验", + "quiz": [ + { + "questionText": "K-Means是源自于哪个领域？", + "answerOptions": [ + { + "answerText": "电气工程", + "isCorrect": "false" + }, + { + "answerText": "信号处理", + "isCorrect": "true" + }, + { + "answerText": "计算语言学", + "isCorrect": "false" + } + ] + }, + { + "questionText": "一个较高的Silhouette分数表示：", + "answerOptions": [ + { + "answerText": "聚类分离度和聚类定义度高", + "isCorrect": "true" + }, + { + "answerText": "聚类数量较少", + "isCorrect": "false" + }, + { + "answerText": "聚类数量较多", + "isCorrect": "false" + } + ] + }, + { + "questionText": "方差是什么？", + "answerOptions": [ + { + "answerText": "距离均值的平方差值的平均数", + "isCorrect": "false" + }, + { + "answerText": "如果方差过高，则会影响聚类结果", + "isCorrect": "false" + }, + { + "answerText": "以上两个选项都正确", + "isCorrect": "true" + } + ] + } + ] + }, + { + "id": 30, + "title": "K-Means聚类: 课后测验", + "quiz": [ + { + "questionText": "沃罗诺伊图显示了什么？", + "answerOptions": [ + { + "answerText": "聚类的方差", + "isCorrect": "false" + }, + { + "answerText": "聚类的质心和其区域", + "isCorrect": "true" + }, + { + "answerText": "聚类的惯性", + "isCorrect": "false" + } + ] + }, + { + "questionText": "惯性是什么？", + "answerOptions": [ + { + "answerText": "聚类内部的一致性度量", + "isCorrect": "true" + }, + { + "answerText": "聚类的移动度量", + "isCorrect": "false" + }, + { + "answerText": "聚类质量的度量", + "isCorrect": "false" + } + ] + }, + { + "questionText": "使用K-Means聚类，必须先确定'k'的值。", + "answerOptions": [ + { + "answerText": "正确", + "isCorrect": "true" + }, + { + "answerText": "错误", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 31, + "title": "自然语言处理简介：课前测验", + "quiz": [ + { + "questionText": "在这些课程中，NLP代表什么?", + "answerOptions": [ + { + "answerText": "神经语言处理", + "isCorrect": "false" + }, + { + "answerText": "自然语言处理", + "isCorrect": "true" + }, + { + "answerText": "自然语言学处理", + "isCorrect": "false" + } + ] + }, + { + "questionText": "Eliza是一个早期的聊天机器人，充当了一个什么样的角色?", + "answerOptions": [ + { + "answerText": "治疗师", + "isCorrect": "true" + }, + { + "answerText": "医生", + "isCorrect": "false" + }, + { + "answerText": "护士", + "isCorrect": "false" + } + ] + }, + { + "questionText": "Alan Turing的“图灵测试”试图确定计算机是否", + "answerOptions": [ + { + "answerText": "无法区分与人类相似", + "isCorrect": "false" + }, + { + "answerText": "思考", + "isCorrect": "false" + }, + { + "answerText": "以上两者皆是", + "isCorrect": "true" + } + ] + } + ] + }, + { + "id": 32, + "title": "自然语言处理简介：课后测验", + "quiz": [ + { + "questionText": "Joseph Weizenbaum发明了哪个聊天机器人?", + "answerOptions": [ + { + "answerText": "Elisha", + "isCorrect": "false" + }, + { + "answerText": "Eliza", + "isCorrect": "true" + }, + { + "answerText": "Eloise", + "isCorrect": "false" + } + ] + }, + { + "questionText": "对话机器人的输出是基于什么的?", + "answerOptions": [ + { + "answerText": "随机选择预定义的选项", + "isCorrect": "false" + }, + { + "answerText": "分析输入并使用机器智能", + "isCorrect": "false" + }, + { + "answerText": "以上两者皆是", + "isCorrect": "true" + } + ] + }, + { + "questionText": "如何让聊天机器人更有效?", + "answerOptions": [ + { + "answerText": "多问一些问题。", + "isCorrect": "false" + }, + { + "answerText": "通过提供更多的数据并相应地进行训练来提高聊天机器人的效果", + "isCorrect": "true" + }, + { + "answerText": "聊天机器人是笨蛋，它不能学习 :(", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 33, + "title": "自然语言处理任务：课前测验", + "quiz": [ + { + "questionText": "分词", + "answerOptions": [ + { + "answerText": "通过标点符号分割文本", + "isCorrect": "false" + }, + { + "answerText": "将文本分割成单独的标记（单词）", + "isCorrect": "true" + }, + { + "answerText": "将文本分割成短语", + "isCorrect": "false" + } + ] + }, + { + "questionText": "嵌入", + "answerOptions": [ + { + "answerText": "将文本数据数字化，以便单词可以聚类", + "isCorrect": "true" + }, + { + "answerText": "将单词嵌入短语中", + "isCorrect": "false" + }, + { + "answerText": "将句子嵌入段落中", + "isCorrect": "false" + } + ] + }, + { + "questionText": "词性标注", + "answerOptions": [ + { + "answerText": "将句子按其词性分割", + "isCorrect": "false" + }, + { + "answerText": "对分词后的单词进行词性标注", + "isCorrect": "true" + }, + { + "answerText": "绘制句子的图表", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 34, + "title": "自然语言处理任务：课后测验", + "quiz": [ + { + "questionText": "使用以下哪种方法构建单词重复出现频率的字典：", + "answerOptions": [ + { + "answerText": "单词和短语词典", + "isCorrect": "false" + }, + { + "answerText": "单词和短语频率", + "isCorrect": "true" + }, + { + "answerText": "单词和短语库", + "isCorrect": "false" + } + ] + }, + { + "questionText": "N-gram是指", + "answerOptions": [ + { + "answerText": "将文本分割成一组特定长度的单词序列", + "isCorrect": "true" + }, + { + "answerText": "将单词分割成一组特定长度的字符序列", + "isCorrect": "false" + }, + { + "answerText": "将文本分割成一组特定长度的段落", + "isCorrect": "false" + } + ] + }, + { + "questionText": "情感分析", + "answerOptions": [ + { + "answerText": "分析一段话的积极或消极情绪", + "isCorrect": "true" + }, + { + "answerText": "分析一段话的情感色彩", + "isCorrect": "false" + }, + { + "answerText": "分析一段话的悲伤程度", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 35, + "title": "自然语言处理和翻译：课前测验", + "quiz": [ + { + "questionText": "朴素翻译", + "answerOptions": [ + { + "answerText": "仅翻译单词", + "isCorrect": "true" + }, + { + "answerText": "翻译句子结构", + "isCorrect": "false" + }, + { + "answerText": "翻译情感", + "isCorrect": "false" + } + ] + }, + { + "questionText": "一个文本语料库指", + "answerOptions": [ + { + "answerText": "少量的文本", + "isCorrect": "false" + }, + { + "answerText": "大量的文本", + "isCorrect": "true" + }, + { + "answerText": "一个标准的文本", + "isCorrect": "false" + } + ] + }, + { + "questionText": "如果一个机器学习模型有足够的人类翻译来构建一个模型，那么它可以", + "answerOptions": [ + { + "answerText": "缩写翻译", + "isCorrect": "false" + }, + { + "answerText": "标准化翻译", + "isCorrect": "false" + }, + { + "answerText": "提高翻译的准确性", + "isCorrect": "true" + } + ] + } + ] + }, + { + "id": 36, + "title": "自然语言处理和翻译：课后测验", + "quiz": [ + { + "questionText": "TextBlob翻译库的基础是：", + "answerOptions": [ + { + "answerText": "Google翻译", + "isCorrect": "true" + }, + { + "answerText": "必应", + "isCorrect": "false" + }, + { + "answerText": "一个自定义的机器学习模型", + "isCorrect": "false" + } + ] + }, + { + "questionText": "要使用'blob.translate'，您需要：", + "answerOptions": [ + { + "answerText": "一个互联网连接", + "isCorrect": "true" + }, + { + "answerText": "一本字典", + "isCorrect": "false" + }, + { + "answerText": "JavaScript", + "isCorrect": "false" + } + ] + }, + { + "questionText": "要确定情感，机器学习方法是：", + "answerOptions": [ + { + "answerText": "将回归技术应用于手动生成的意见和分数，寻找模式", + "isCorrect": "false" + }, + { + "answerText": "将自然语言处理技术应用于手动生成的意见和分数，寻找模式", + "isCorrect": "true" + }, + { + "answerText": "将聚类技术应用于手动生成的意见和分数，寻找模式", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 37, + "title": "自然语言处理 4: 课前测验", + "quiz": [ + { + "questionText": "人类写下或说出的文本可以提供什么信息？", + "answerOptions": [ + { + "answerText": "模式和频率", + "isCorrect": "false" + }, + { + "answerText": "情感和意义", + "isCorrect": "false" + }, + { + "answerText": "以上两者", + "isCorrect": "true" + } + ] + }, + { + "questionText": "什么是情感分析？", + "answerOptions": [ + { + "answerText": "研究家庭传家宝是否有情感价值的一种方法", + "isCorrect": "false" + }, + { + "answerText": "系统地识别、提取、量化和研究情感状态和主观信息的方法", + "isCorrect": "true" + }, + { + "answerText": "判断某人是悲伤还是快乐的能力", + "isCorrect": "false" + } + ] + }, + { + "questionText": "使用酒店评论数据集、Python和情感分析可以回答什么问题？", + "answerOptions": [ + { + "answerText": "评论中最常用的词和短语是什么？", + "isCorrect": "true" + }, + { + "answerText": "哪个度假村的游泳池最好？", + "isCorrect": "false" + }, + { + "answerText": "这家酒店是否提供代客停车服务？", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 38, + "title": "自然语言处理4: 课后测验", + "quiz": [ + { + "questionText": "自然语言处理的本质是什么？", + "answerOptions": [ + { + "answerText": "将人类语言分类为快乐或悲伤", + "isCorrect": "false" + }, + { + "answerText": "解释意义或情感，而无需人为干预", + "isCorrect": "true" + }, + { + "answerText": "找到情感的异常值并进行检查", + "isCorrect": "false" + } + ] + }, + { + "questionText": "在清理数据时，您可能会查找哪些内容？", + "answerOptions": [ + { + "answerText": "其他语言中的字符", + "isCorrect": "false" + }, + { + "answerText": "空白行或列", + "isCorrect": "false" + }, + { + "answerText": "以上两者", + "isCorrect": "true" + } + ] + }, + { + "questionText": "在对数据执行操作之前，了解数据及其怪癖很重要。", + "answerOptions": [ + { + "answerText": "正确", + "isCorrect": "true" + }, + { + "answerText": "错误", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 39, + "title": "自然语言处理5：课前测验", + "quiz": [ + { + "questionText": "为什么在分析数据之前清洗数据很重要？", + "answerOptions": [ + { + "answerText": "一些列可能缺少或包含不正确的数据", + "isCorrect": "false" + }, + { + "answerText": "杂乱的数据可能会导致关于数据集的错误结论", + "isCorrect": "false" + }, + { + "answerText": "以上两种情况都是", + "isCorrect": "true" + } + ] + }, + { + "questionText": "清洗数据的策略示例是什么？", + "answerOptions": [ + { + "answerText": "删除不适用于回答特定问题的列/行", + "isCorrect": "true" + }, + { + "answerText": "摆脱与假设不符的经过验证的值", + "isCorrect": "false" + }, + { + "answerText": "将异常值移动到单独的表中，并运行该表的计算以查看它们是否匹配", + "isCorrect": "false" + } + ] + }, + { + "questionText": "使用标签列对数据进行分类可能很有用。", + "answerOptions": [ + { + "answerText": "正确", + "isCorrect": "true" + }, + { + "answerText": "错误", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 40, + "title": "自然语言处理5: 课后测验", + "quiz": [ + { + "questionText": "数据集的目标是什么？", + "answerOptions": [ + { + "answerText": "查看全球酒店的积极和消极评价数量", + "isCorrect": "false" + }, + { + "answerText": "添加情感和列，以帮助您选择最佳酒店", + "isCorrect": "true" + }, + { + "answerText": "分析为什么人们会留下特定的评价", + "isCorrect": "false" + } + ] + }, + { + "questionText": "什么是停用词？", + "answerOptions": [ + { + "answerText": "不改变句子情感的常见英语单词", + "isCorrect": "false" + }, + { + "answerText": "可以删除以加快情感分析的单词", + "isCorrect": "false" + }, + { + "answerText": "以上两者皆是", + "isCorrect": "true" + } + ] + }, + { + "questionText": "为了测试情感分析，必须确保其与同一评价的评论者得分相匹配。", + "answerOptions": [ + { + "answerText": "正确", + "isCorrect": "true" + }, + { + "answerText": "错误", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 41, + "title": "时间序列简介：课前测验", + "quiz": [ + { + "questionText": "时间序列预测在以下方面有用：", + "answerOptions": [ + { + "answerText": "确定未来成本", + "isCorrect": "false" + }, + { + "answerText": "预测未来价格", + "isCorrect": "false" + }, + { + "answerText": "以上两种情况", + "isCorrect": "true" + } + ] + }, + { + "questionText": "时间序列是一系列在以下哪些时间点上获取的序列？", + "answerOptions": [ + { + "answerText": "空间中连续等间隔点", + "isCorrect": "false" + }, + { + "answerText": "时间中连续等间隔点", + "isCorrect": "true" + }, + { + "answerText": "空间和时间中连续等间隔点", + "isCorrect": "false" + } + ] + }, + { + "questionText": "时间序列可以用于以下哪些方面？", + "answerOptions": [ + { + "answerText": "地震预测", + "isCorrect": "true" + }, + { + "answerText": "计算机视觉", + "isCorrect": "false" + }, + { + "answerText": "颜色分析", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 42, + "title": "时间序列简介：课后测验", + "quiz": [ + { + "questionText": "时间序列趋势是指：", + "answerOptions": [ + { + "answerText": "随时间可测量的增长和减少", + "isCorrect": "true" + }, + { + "answerText": "时间上量化的减少", + "isCorrect": "false" + }, + { + "answerText": "时间上增长和减少之间的间隙", + "isCorrect": "false" + } + ] + }, + { + "questionText": "异常值是指：", + "answerOptions": [ + { + "answerText": "接近标准数据方差的点", + "isCorrect": "false" + }, + { + "answerText": "远离标准数据方差的点", + "isCorrect": "true" + }, + { + "answerText": "在标准数据方差范围内的点", + "isCorrect": "false" + } + ] + }, + { + "questionText": "时间序列预测对于以下哪个领域最有用？", + "answerOptions": [ + { + "answerText": "计量经济学", + "isCorrect": "true" + }, + { + "answerText": "历史学", + "isCorrect": "false" + }, + { + "answerText": "图书馆", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 43, + "title": "时间序列ARIMA: 课前测验", + "quiz": [ + { + "questionText": "ARIMA代表什么？", + "answerOptions": [ + { + "answerText": "自回归积分移动平均", + "isCorrect": "false" + }, + { + "answerText": "自回归积分移动操作", + "isCorrect": "false" + }, + { + "answerText": "自回归积分移动平均", + "isCorrect": "true" + } + ] + }, + { + "questionText": "平稳性是指", + "answerOptions": [ + { + "answerText": "数据在时间上移动时其属性不变", + "isCorrect": "false" + }, + { + "answerText": "数据在时间上移动时其分布不变", + "isCorrect": "true" + }, + { + "answerText": "数据在时间上移动时其分布发生变化", + "isCorrect": "false" + } + ] + }, + { + "questionText": "差分", + "answerOptions": [ + { + "answerText": "稳定趋势和季节性", + "isCorrect": "false" + }, + { + "answerText": "加剧趋势和季节性", + "isCorrect": "false" + }, + { + "answerText": "消除趋势和季节性", + "isCorrect": "true" + } + ] + } + ] + }, + { + "id": 44, + "title": "时间序列 ARIMA：课后测验", + "quiz": [ + { + "questionText": "ARIMA 用于使模型适合时间序列数据的特殊形式", + "answerOptions": [ + { + "answerText": "尽可能平坦", + "isCorrect": "false" + }, + { + "answerText": "尽可能贴近", + "isCorrect": "true" + }, + { + "answerText": "通过散点图", + "isCorrect": "false" + } + ] + }, + { + "questionText": "使用SARIMAX来", + "answerOptions": [ + { + "answerText": "管理季节性 ARIMA 模型", + "isCorrect": "true" + }, + { + "answerText": "管理特殊 ARIMA 模型", + "isCorrect": "false" + }, + { + "answerText": "管理统计 ARIMA 模型", + "isCorrect": "false" + } + ] + }, + { + "questionText": "“向前走”验证涉及", + "answerOptions": [ + { + "answerText": "逐步重新评估验证的模型", + "isCorrect": "false" + }, + { + "answerText": "逐步重新训练验证的模型", + "isCorrect": "true" + }, + { + "answerText": "逐步重新配置验证的模型", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 45, + "title": "强化学习1：课前测验", + "quiz": [ + { + "questionText": "什么是强化学习？", + "answerOptions": [ + { + "answerText": "反复教导某人某事直到他们理解为止的学习技巧", + "isCorrect": "false" + }, + { + "answerText": "一种学习技术，通过运行许多实验来解释某种环境中代理的最佳行为", + "isCorrect": "true" + }, + { + "answerText": "了解如何同时运行多个实验的技巧", + "isCorrect": "false" + } + ] + }, + { + "questionText": "什么是策略？", + "answerOptions": [ + { + "answerText": "返回任何给定状态的动作的函数", + "isCorrect": "true" + }, + { + "answerText": "告诉你是否可以退货的文件", + "isCorrect": "false" + }, + { + "answerText": "用于随机目的的函数", + "isCorrect": "false" + } + ] + }, + { + "questionText": "奖励函数返回环境中每个状态的分数。", + "answerOptions": [ + { + "answerText": "正确", + "isCorrect": "true" + }, + { + "answerText": "错误", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 46, + "title": "强化学习1：课后测验", + "quiz": [ + { + "questionText": "什么是Q-Learning？", + "answerOptions": [ + { + "answerText": "记录每个状态的“好”程度的机制", + "isCorrect": "false" + }, + { + "answerText": "一种策略由Q-表定义的算法", + "isCorrect": "false" + }, + { + "answerText": "以上都是", + "isCorrect": "true" + } + ] + }, + { + "questionText": "Q-表对应于随机行走策略的哪些值？", + "answerOptions": [ + { + "answerText": "所有相等的值", + "isCorrect": "true" + }, + { + "answerText": "-0.25", + "isCorrect": "false" + }, + { + "answerText": "所有不同的值", + "isCorrect": "false" + } + ] + }, + { + "questionText": "在我们的课程中，学习过程中使用探索比开发更好。", + "answerOptions": [ + { + "answerText": "正确", + "isCorrect": "false" + }, + { + "answerText": "错误", + "isCorrect": "true" + } + ] + } + ] + }, + { + "id": 47, + "title": "强化学习 2：课前测验", + "quiz": [ + { + "questionText": "国际象棋和围棋是具有连续状态的游戏。", + "answerOptions": [ + { + "answerText": "正确", + "isCorrect": "false" + }, + { + "answerText": "错误", + "isCorrect": "true" + } + ] + }, + { + "questionText": "什么是 CartPole 问题？", + "answerOptions": [ + { + "answerText": "一种排除异常值的过程", + "isCorrect": "false" + }, + { + "answerText": "一种优化购物车的方法", + "isCorrect": "false" + }, + { + "answerText": "平衡的简化版本", + "isCorrect": "true" + } + ] + }, + { + "questionText": "我们可以使用哪个工具来模拟游戏中潜在状态的不同情况？", + "answerOptions": [ + { + "answerText": "猜测和检查", + "isCorrect": "false" + }, + { + "answerText": "模拟环境", + "isCorrect": "true" + }, + { + "answerText": "状态转换测试", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 48, + "title": "强化学习2：课后测验", + "quiz": [ + { + "questionText": "我们在环境中哪里定义了所有可能的动作？", + "answerOptions": [ + { + "answerText": "方法", + "isCorrect": "false" + }, + { + "answerText": "动作空间", + "isCorrect": "true" + }, + { + "answerText": "动作列表", + "isCorrect": "false" + } + ] + }, + { + "questionText": "我们使用哪对作为字典键值对？", + "answerOptions": [ + { + "answerText": "(状态，动作) 作为键，Q表条目作为值", + "isCorrect": "true" + }, + { + "answerText": "状态作为键，动作作为值", + "isCorrect": "false" + }, + { + "answerText": "qvalues函数的值作为键，动作作为值", + "isCorrect": "false" + } + ] + }, + { + "questionText": "我们在Q学习期间使用的超参数是什么？", + "answerOptions": [ + { + "answerText": "q表值，当前奖励，随机动作", + "isCorrect": "false" + }, + { + "answerText": "学习率，折扣因子，探索/开发因子", + "isCorrect": "true" + }, + { + "answerText": "累积奖励，学习率，探索因子", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 49, + "title": "真实世界的应用：课前测验", + "quiz": [ + { + "questionText": "金融行业中的机器学习应用示例是什么？", + "answerOptions": [ + { + "answerText": "使用自然语言处理个性化客户旅程", + "isCorrect": "false" + }, + { + "answerText": "使用线性回归进行财富管理", + "isCorrect": "true" + }, + { + "answerText": "使用时间序列进行能源管理", + "isCorrect": "false" + } + ] + }, + { + "questionText": "医院可以使用哪种机器学习技术来管理再次入院？", + "answerOptions": [ + { + "answerText": "聚类", + "isCorrect": "true" + }, + { + "answerText": "时间序列", + "isCorrect": "false" + }, + { + "answerText": "自然语言处理", + "isCorrect": "false" + } + ] + }, + { + "questionText": "时间序列在能源管理中的应用示例是什么？", + "answerOptions": [ + { + "answerText": "动物运动检测", + "isCorrect": "false" + }, + { + "answerText": "智能停车计费系统", + "isCorrect": "true" + }, + { + "answerText": "追踪森林火灾", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 50, + "title": "实际应用：课后测验", + "quiz": [ + { + "questionText": "哪种机器学习技术可以用于检测信用卡欺诈？", + "answerOptions": [ + { + "answerText": "回归", + "isCorrect": "false" + }, + { + "answerText": "聚类", + "isCorrect": "true" + }, + { + "answerText": "自然语言处理", + "isCorrect": "false" + } + ] + }, + { + "questionText": "森林管理中展示了哪种机器学习技术？", + "answerOptions": [ + { + "answerText": "强化学习", + "isCorrect": "true" + }, + { + "answerText": "时间序列", + "isCorrect": "false" + }, + { + "answerText": "自然语言处理", + "isCorrect": "false" + } + ] + }, + { + "questionText": "在医疗保健行业中，哪种是机器学习应用的例子？", + "answerOptions": [ + { + "answerText": "使用回归预测学生行为", + "isCorrect": "false" + }, + { + "answerText": "使用分类器管理临床试验", + "isCorrect": "true" + }, + { + "answerText": "使用分类器检测动物的运动", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 51, + "title": "时间序列SVR: 课前测验", + "quiz": [ + { + "questionText": "SVM 代表什么？", + "answerOptions": [ + { + "answerText": "统计向量机", + "isCorrect": "false" + }, + { + "answerText": "支持向量机", + "isCorrect": "true" + }, + { + "answerText": "统计向量模型", + "isCorrect": "false" + } + ] + }, + { + "questionText": "以下哪种机器学习技术用于预测连续值？", + "answerOptions": [ + { + "answerText": "聚类", + "isCorrect": "false" + }, + { + "answerText": "分类", + "isCorrect": "false" + }, + { + "answerText": "回归", + "isCorrect": "true" + } + ] + }, + { + "questionText": "以下哪个模型通常用于时间序列预测？", + "answerOptions": [ + { + "answerText": "ARIMA", + "isCorrect": "true" + }, + { + "answerText": "K-Means聚类", + "isCorrect": "false" + }, + { + "answerText": "逻辑回归", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 52, + "title": "时间序列 SVR: 课后测验", + "quiz": [ + { + "questionText": "SVR 通过哪些方法学习?", + "answerOptions": [ + { + "answerText": "寻找具有最大数据点的最佳拟合超平面", + "isCorrect": "true" + }, + { + "answerText": "学习数据集的概率分布", + "isCorrect": "false" + }, + { + "answerText": "在数据集中找到聚类", + "isCorrect": "false" + } + ] + }, + { + "questionText": "SVM 中核函数的目的是什么?", + "answerOptions": [ + { + "answerText": "衡量模型预测的准确性", + "isCorrect": "false" + }, + { + "answerText": "将数据集转换到更高的维度空间", + "isCorrect": "true" + }, + { + "answerText": "标准化数据集的值", + "isCorrect": "false" + } + ] + }, + { + "questionText": "哪种模型考虑数据集的非线性?", + "answerOptions": [ + { + "answerText": "简单线性回归", + "isCorrect": "false" + }, + { + "answerText": "ARIMA", + "isCorrect": "false" + }, + { + "answerText": "使用 RBF 核的 SVR", + "isCorrect": "true" + } + ] + } + ] + } + ] + } +] \ No newline at end of file