You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
18 lines
765 B
18 lines
765 B
# Name generation using Recurrent Neural Networks
|
|
|
|
**Tier:** 2-Intermediate
|
|
|
|
Name Generation is nothing more than a sequence of letters that follow certain patterns to create a certain probability density for choosing the next letter in a name.
|
|
This App should utilize a RNN model with LSTM/GRUs to ensure highly likeable naming patterns
|
|
|
|
## User Stories
|
|
|
|
- [ ] User can specify the first 2 to 3 letters to be used for the initial name
|
|
- [ ] Use can see the generated name and use it accordingly
|
|
|
|
|
|
## Useful links and resources
|
|
|
|
- [RNN for Pokemon names](https://towardsdatascience.com/generating-pok%C3%A9mon-names-using-rnns-f41003143333)
|
|
- [RNN for Dinosaur names](https://datascience-enthusiast.com/DL/Dinosaurus_Island_Character_level_language_model.html)
|