Calendar
Supervised learning
- Jan 24
- Jan 31
-
- Distributed representation of words
- Learning word vectors
- Section Operations on word vectors [slides][notebook]
- Feb 7
-
- Sequence modeling [recording]
- HW 1 due
- HW 2 out[zip]
-
- Neural network basics
- RNN and its variants
- Attention and Transformers
- SectionHPC tutorial and Pytorch tutorial
- Feb 14
-
- Encoder-decoder models
- Decoding algorithms
- Machine translation and evaluation
- Feb 21
-
- The landscape of NLP tasks
- Evaluation
- Final project tips
- Section NLP benchmarks [slides][notebook]
Representation learning
- Feb 28
-
- Pretrain then finetune [recording]
- HW 2 due
-
- Data
- Self-supervised learning
- Adaptation / finetuning
- SectionHuggingface transformer
- Mar 7
- Online midterm (no lecture)
- Mar 14
-
- Spring break (no lecture)
- Mar 21
-
- Advanced pretraining and finetuning techniques [recording]
- proposal due
- HW 3 out[zip]
-
- Efficient pretraining
- Efficient finetuning
- Additional reading: Efficient transformers: a survey
- Mar 28
-
- Behavioral tests
- Fairness, robustness, privacy
- Additional reading: Holistic evaluation of language models
NLP via language modeling
- Apr 4
-
- N-gram language models
- Neural autoregressive language models
- Language models as general task solvers
- SectionPrompt engineering
- Apr 11
-
- Scaling language models (by Jason Wei) [recording]
- HW 3 due
-
- Scaling laws
- Emergent abilities
- Reasoning
- Apr 18
-
- Why do we need alignment?
- Approaches to alignment
- Tips on project presentation and report
- Apr 25
-
- Instruction tuning
- RLHF
- May 2
-
- Project presentation
- Report due