Guest
We implement a multilayer perceptron (MLP) character-level language model. In this video we also introduce many basics of machine learning (e.g. model training, learning rate tuning, hyperparameters, evaluation, train/dev/test splits, under/overfitting, etc.). Links: - makemore on github: - jupyter notebook I built in this video: - collab notebook (new)!!!: - Bengio et al. 2003 MLP language model paper (pdf): Useful links: - PyTorch internals ref Exercises: - E01: Tune the hyperparameters of the training to beat my best validation loss of 2.2 - E02: I was not careful with the intialization of the network in this video. (1) What is the loss you’d get if the predicted probabilities at initialization were perfectly uniform? What loss do we achieve? (2) Can you tune the initialization to get a starting loss that is much more similar to (1)? - E03: Read the Bengio et al 2003 paper (link above), implement and try any idea from the paper. Did it work? Chapters: 00:00:00 intro 00:01:48 Bengio et al. 2003 (MLP language model) paper walkthrough 00:09:03 (re-)building our training dataset 00:12:19 implementing the embedding lookup table 00:18:35 implementing the hidden layer internals of : storage, views 00:29:15 implementing the output layer 00:29:53 implementing the negative log likelihood loss 00:32:17 summary of the full network 00:32:49 introducing and why 00:37:56 implementing the training loop, overfitting one batch 00:41:25 training on the full dataset, minibatches 00:45:40 finding a good initial learning rate 00:53:20 splitting up the dataset into train/val/test splits and why 01:00:49 experiment: larger hidden layer 01:05:27 visualizing the character embeddings 01:07:16 experiment: larger embedding size 01:11:46 summary of our final code, conclusion 01:13:24 sampling from the model 01:14:55 google collab (new!!) notebook advertisement
