Udacity Deep Learning Nanodegree Project #3.
Objective: Generate your own Seinfeld TV scripts using RNNs. The input data was Seinfeld dataset of scripts from 9 seasons. The Neural Network you'll build will generate a new ,"fake" TV script, based on patterns it recognizes in this training data.
What I learnt:
- Lookup Table
- Tokenize Punctuation
- Batching the data
- Creating dataloaders
- Initializing RNN model and defining layers
- Forward propagation of the neural network
- Initialize the hidden state of an LSTM/GRU
- Apply forward and back propagation
- Setting the hyperparameters for optimal loss values.