Link Search Menu Expand Document

A tentative plan for the schedule (topics, deadlines, etc.) is available here.

CS 4650 covers the foundations of Deep Learning for Natural Language Processing, including mathematical foundations, neural networks, classic algorithms such as Viterbi, the origins of language modeling development, and evaluation methods such as F1 and MT metrics.

For more cutting-edge LLM topics, we have developed a dedicated course, CS 7652 “Large Language Models”, which we recommend taking after CS 4650.

Schedule (subject to change as the term progresses)

Resource
PyTorch Tutorial (w/ links to Colab notebook)
TBA
Course Overview
Eisenstein 1
TBA (to be updated)
Machine Learning Review - linear classification
Eisenstein 1, J+M 4
TBA
Machine Learning Review - logistic regression, perceptron, SVM
Eisenstein 2.0-2.5, 4.1, 4.3-4.5, J+M B
TBA
Machine Learning Review - mutliclass classification
Eisenstein 2.0-2.5, 4.1, 4.3-4.5, J+M 4
TBA
Neural Networks - Feedforward, optimization
Eisenstein 2.6, 3.1-3.3, J+M 6, Goldberg 1-4, J.G. Makin - Backpropagation
TBA
Word Embeddings
Eisenstein 3.3.4, 14.5, 14.6, J+M 5, Goldberg 5
TBA
Sequence Models - HMM, Viterbi
Eisenstein 7.0-7.4, J+M 17, J+M A
TBA
Conditional Random Fields
Eisenstein 7.5, 8.3, J+M 17
TBA
Recurrent Neural Networks + Neural CRFs
Eisenstein 3.4, 7.6, Goldberg 10-11, J+M 13
TBA
Encoder-Decoder + Attention
Eisenstein 18.3 - 18.5
TBA
Transformer
J+M 8, Vaswani+17 Transformers, Alammar’s blog post, Rush’s tutorial
TBA
Convolutional Neural Networks, MT Evaluation
Eisenstein 3.4, 7.6, Goldberg 9
TBA
Pretrained Language Models - part 1 (ELMo, BERT & variants, BART/T5)
J+M 10, ELMo BERT, BART
TBA
Pretrained Language Models - part 2 (GPT2/3, knowledge distillation, instruction tuning)
J+M 7, Hinton+15 Knowledge Distillation, GPT-3
TBA
Post-training of Language Models - part 3 (InstructGPT, preference optimization, decoding), Midterm Review
InstructGPT
TBA
Open-source Language Models - part 4 (LLaMA, normalization, RoPE, AdamW, etc.)
Llama 3
TBA
Open-source Language Models - part 5 (tokenization, BPE, multilinguality))
BPE
TBA
In-class Midterm (close book, close note)