Notes will sometimes be posted in advance, but all notes are subject to change.
Lectures | Reading and Materials | |
---|---|---|
Week 1 |
Lecture 1: Quick review of Maximum Likelihood, Bayesian inference, torch_coin_manual.py. Lecture 2: Bayesian inference (and unicorns). Code: coin_bayes.py Lecture 3.1 Generative models Lecture 3: Causal inference Videos: |
Reading:
|
Week 2 |
Slides: Intro to fairness in ML. Zoom recording |
Reading:
|
Week 3 |
Lecture 1a: causal.py, explain_away.py Lecture 1b: Fairness and causality. Lecture 2: Causality and ML Zoom recording (notes coming up) |
Reading: Kusner et al., Counterfactual Fairness, NeuriPS 2017 Reading: Mitchell at al., Model Cards for Model Reporting, FAT* 19 Reading: Shoelkopf et al., Toward Causal Representation Learning, Proc. of the IEEE, 2021 Video: Yoshua Bengio, Towards Causal Representation Learning |
Week 4 |
Lectures 1, 2: Causality and ML, continued Lecture 3: Word embeddings, subword models from the Transformers lecture |
Reading: continue reading last week's readings on causaltion Reading: We mentioned in lecture that PCA can be seen as finding the basis vectors that minimize the reconstruction error. Also see Slides 1-10 here Reading: Notes on Word2vec and GLoVe. The original GloVe paper, original Word2vec paper (not super-readable), an explanation of the original Word2vec paper Reading: Byte-pair encoding Just for fun: Why Athletes' Birthdays Affect Who Goes Pro — And Who Becomes A Star Just for fun: Publication bias |
Week 5 |
Lecture: Transformers. Zoom recording. |
Reading: The Illustrated Transformer |
Week 6 |
Lecture: Transformers, cont'd. Capabilities of transformers. Zoom recording Code: MinGPT |
Reading:
|
Week 7 |
Lecture: More details on PyTorch. GANs. Zoom recording |
Reading:
|
Week 8 | GANs. Started WGANs | Reading:
|
Week 9 |
WGANs continued. |
Reading:
|
Week 10 |
Handout: working with distances between distributions WGANs continued. |
|
Week 11 |
Variational Autoencoders, cont'd |
Readable summary: Weng, From Autoencoder to Beta-VAE: the VAE section, blog post, 2018 |
Week 12 | ||
Week 13 |
Grokking, scaling, and all that Metalearning (not on the exam) |