A tentative plan for the schedule (topics, deadlines, etc.) is available here.
Schedule (subject to change as the term progresses)
- Resource
- PyTorch Tutorial (w/ links to Colab notebook)
- Aug 18
- Course Overview
- Eisenstein 1
- Aug 20
- Machine Learning Review - linear classification
- Eisenstein 1, J+M 4
- Aug 21
- Problem Set 0 due
- Aug 25
- Machine Learning Review - logistic regression, perceptron, SVM
- Eisenstein 2.0-2.5, 4.1, 4.3-4.5, J+M 5
- Aug 27
- Machine Learning Review - mutliclass classification
- Eisenstein 2.0-2.5, 4.1, 4.3-4.5, J+M 5
- Aug 29
- Project 0 due
- Neural Networks - Feedforward, optimization
- Eisenstein 2.6, 3.1-3.3, J+M 7, Goldberg 1-4, J.G. Makin - Backpropagation
- Word Embeddings
- Eisenstein 3.3.4, 14.5, 14.6, J+M 6, Goldberg 5
- Sequence Models - HMM, Viterbi
- Eisenstein 7.0-7.4, J+M 17, J+M A
- Conditional Random Fields
- Eisenstein 7.5, 8.3
- Recurrent Neural Networks
- Eisenstein 7.6, Goldberg 10-11, J+M 8
- Convolutional Neural Networks + Neural CRFs
- Eisenstein 3.4, 7.6, Goldberg 9
- Encoder-Decoder + MT
- Eisenstein 18.3 - 18.5
- Attention+ Tokenization
- Wu+16 Google NMT, Holtzman+19 Degeneration
- Transformer
- J+M 9, Vaswani+17 Transformers, Alammar’s blog post, Rush’s tutorial
- Pretrained Language Models (part 1)
- J+M 11, ELMo BERT
- Pretrained Language Models (part 2) + Ethics
- J+M 10, BART, GPT-3
- Post-training of Language Models (part 3)
- InstructGPT
- Open-source Language Models (part 4)
- Llama 3
In-class Midterm (close book, close note)