Thanks to Sabrina Recoule Quang, also in the course, I discovered Max Woolf’s repo for neural text generation (using LSTMs). The project in built in Keras/TensorFlow. This will certainly be a stepping stone for my study of these networks and text generatio in general. The goal is clear: make experiments generating texts, but also, hopefully soon, pick apart the code and gradually acquire the skills to build such networks myself.


He is himself, however, a student of Karpathy’s, whose char-rnn model is the foundation of Woolf’s project.

The transition from Karpathy’s code into TensorFlow is already a well-trodden path, see here, here, here and there. I’m assuming that Parag Mital’s Char RNN model, available in his Kadenze course, is also based on the same architecture.