Z2H Video 2, round 2 [Post #14, Day 30]

PyTorch is a deep learning neural network framework.

Part 1: bigram language modeling, explicit (statistical) approach

1. Intro to makemore, "makemore takes one text file as input, where each line is assumed to be one training thing, and generates more things like it"
2. Names data set, quick analysis of data set
3. Divide up all the bigrams in the names data set and keep counts of them in a dictionary

4. PyTorch tensor to store bigram counts instead (27 x 27 tensor)

5. Summary

Part 2: bigram language modeling, neural net approach