Neural Networks with Keras Cookbook

Getting ready

The strategy that we'll adopt to generate text is as follows:

1. Import project Gutenberg's Alice's Adventures in Wonderland dataset, which can be downloaded from https://www.gutenberg.org/files/11/11-0.txt.

2. Preprocess the text data so that we bring every word to the same case, and remove punctuation.
3. Assign an ID to each unique word and then convert the dataset into a sequence of word IDs.
4. Loop through the total dataset, 10 words at a time. Consider the 10 words as input and the subsequent 11th word as output.
5. Build and train a model, by performing embedding on top of the input word IDs and then connecting the embeddings to an LSTM, which is connected to the output layer through a hidden layer. The value in the output layer ...