DSC 291 Machine Learning with Few Labels

Date	Lecture	Suggested Readings	Logistics
04/01	Lecture #1: Overview [ slides ] [ marked ]
04/03	Lecture #2: Overview [ slides ] [ marked ]
04/08	Lecture #3: Supervised / Unsupervised Learning [ slides ] [ marked ]
04/10	Lecture #4: Unsupervised Learning: EM [ slides ] [ marked ]	PRML, Chapter 9 (Mixture Models and EM)
04/15	Lecture #5: Unsupervised Learning: VAEs [ slides ]	PRML, Chapter 10.1-10.3 (Variational Inference)
04/17	Lecture #6: SUnsupervised Learning: VAEs [ slides ]	Lecun and Misra, (Blog) Self-supervised learning: The dark matter of intelligence (Optional) Devlin et al. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
04/22	Lecture #7: Self-supervised Learning [ slides ] [ marked ]	Deep Learning book, Chap 20.10.3 (Optional) Kingma and Welling, 2014, Variational Autoencoders (Optional) He et al. Masked Autoencoders Are Scalable Vision Learners
04/24	Lecture #8: Self-Supervised Learning [ slides ] [ marked ]	Weng, (Blog) Contrastive Representation Learning (Optional) Ting et al. A Simple Framework for Contrastive Learning of Visual Representations
04/29	Lecture #9: Contrastive Learning [ slides ] [ marked ]	(Optional) Shorten and Khoshgoftaar A survey on Image Data Augmentation for Deep Learning (Optional) Chen et al. An Empirical Survey of Data Augmentation for Limited Data Learning in NLP (Optional) Hu et al. Learning Data Manipulation for Augmentation and Weighting
05/01	Lecture #10: Data Manipulation / Weakly-Supervised Learning [ slides ] [ marked ]	Sachdeva and McAuley Data Distillation: A Survey (Optional) Ratner et al. Snorkel: rapid training data creation with weak supervision
05/06	Lecture #11: Deep Generative Models / Generative Adversarial Learning [ slides ] [ marked ]	Goodfellow et al., Generative Adversarial Nets Deep Learning book, Chap 20.10.4 (Optional) Lil'Log, From GAN to WGAN
05/08	Lecture #12: Generative Adversarial Learning / Reinforcement Learning [ slides ] [ marked ]	(Optional) Lil'Log, What are Diffusion Models? Silver and Sutton, Welcome to the Era of Experience
05/13	Lecture #13: Reinforcement Learning [ slides ] [ marked ]	Lilian Weng, A (Long) Peek into Reinforcement Learning
05/15	Lecture #14: Reinforcement Learning [ slides ] [ marked ]	Huggingface Deep RL Course, Q Learning Guo et al 2022, Efficient (Soft) Q-Learning for Text Generation with Limited Good Data
05/20	Lecture #15: Reinforcement Learning [ slides ]	Sutton, Barto, Reinforcement Learning, An Introduction, Chapter 13.
05/22	Lecture #16: Guest Lecture
05/27	Lecture #17: World Model [ slides ] [ marked ]	Hu and Shu, 2023: Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planning (Optional) Ha and Schmidhuber, 2018: World Models (Optional) Xiang et al., 2024: Pandora: Towards General World Model with Natural Language Actions and Video States
05/29	Lecture #18: Agent Model / Standard Model [ slides ]	(Optional) Hu and Xing, Toward A "Standard Model" of Machine Learning
06/03	Lecture #19: Final project presentation (Zoom)
06/05	Lecture #20: Final project presentation (Zoom)
Final Week			Project final report due

04/01

Lecture #1:
Overview
[ slides ] [ marked ]

04/03

Lecture #2:
Overview
[ slides ] [ marked ]

04/08

Lecture #3:
Supervised / Unsupervised Learning
[ slides ] [ marked ]

04/10

Lecture #4:
Unsupervised Learning: EM
[ slides ] [ marked ]