https://github.com/sushantdhumak/dinosaurus_island_character

Coursera - RNN Programming Assignment: In this project, we are in charge of a special task: Leading biology researchers are creating new breeds of dinosaurs and bringing them to life on earth, and our job is to give names to these dinosaurs. If a dinosaur does not like its name, it might go berserk, so choose wisely!
https://github.com/sushantdhumak/dinosaurus_island_character

gradient-clipping gradient-descent numpy preprocessing rnn sampling

Last synced: 22 days ago
JSON representation

Coursera - RNN Programming Assignment: In this project, we are in charge of a special task: Leading biology researchers are creating new breeds of dinosaurs and bringing them to life on earth, and our job is to give names to these dinosaurs. If a dinosaur does not like its name, it might go berserk, so choose wisely!

• Host: GitHub
• URL: https://github.com/sushantdhumak/dinosaurus_island_character
• Owner: sushantdhumak
• Created: 2021-08-27T18:40:33.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2021-08-29T15:25:21.000Z (over 3 years ago)
• Last Synced: 2025-01-01T18:34:24.113Z (about 2 months ago)
• Topics: gradient-clipping, gradient-descent, numpy, preprocessing, rnn, sampling
• Language: Jupyter Notebook
• Homepage:
• Size: 6.25 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Dinosaurus_Island_Character

## Coursera - RNN Programming Assignment

### Disclaimer:

The given solutions in this project are only for reference purpose.

### Description of experiment

Welcome to Dinosaurus Island! 65 million years ago, dinosaurs existed, and in this assignment, they have returned.

We are in charge of a special task: Leading biology researchers are creating new breeds of dinosaurs and bringing them to life on earth, 

and our job is to give names to these dinosaurs. If a dinosaur does not like its name, it might go berserk, so choose wisely!

Luckily we're equipped with some deep learning now, and you will use it to save the day! 

We have collected a list of all the dinosaur names they could find, and compiled them into this dataset. 

To create new dinosaur names, we will build a character-level language model to generate new names. 

Our algorithm will learn the different name patterns, and randomly generate new names. 

Hopefully this algorithm will keep you and your team safe from the dinosaurs' wrath!

By the time we complete this assignment, we'll be able to:

1. Store text data for processing using an RNN 


2. Build a character-level text generation model using an RNN 


3. Sample novel sequences in an RNN 


4. Explain the vanishing/exploding gradient problem in RNNs 


5. Apply gradient clipping as a solution for exploding gradients 


### Acknowledgements

https://www.coursera.org/learn/nlp-sequence-models 


https://www.deeplearning.ai/program/deep-learning-specialization/