DSC 291 Machine Learning with Few Labels

Date	Lecture	Readings	Logistics
01/09	Lecture #1: Overview [ slides ]
01/11	Lecture #2 ML Basics [ slides ]	M Jordan, The exponential family: Basics
01/13	Lecture #3 ML Basics [ slides ]	PRML, Appendix D. Calculus of Variations
01/16	Martin Luther King, Jr. Holiday (No class)
01/18	Lecture #4 Unsupervised learning [ slides ]	Borman, The EM algorithm (A short tutorial)
01/20	Lecture #5 Unsupervised learning [ slides ]	PRML, Chapter 9 (Mixture Models and EM)
01/23	Lecture #6 Variational Inference [ N/A ]	PRML, Chapter 10.1-10.3 (Variational Inference)
01/25	Lecture #7 Variational Inference [ slides ]	Deep Learning book, Chap 20.10.3 (Variational Autoencoder) (Optional) Kingma and Welling, 2014, Variational Autoencoders
01/27	Lecture #8 Variational Inference [ slides ]	N/A	Project proposal due HW1 out
01/30	Lecture #9 Self-supervised Learning [ 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
02/01	Lecture #10 Self-supervised Learning [ slides ]	Weng, (Blog) Contrastive Representation Learning (Optional) Ting et al. A Simple Framework for Contrastive Learning of Visual Representations
02/03	Lecture #11 Data Manipulation [ slides ]	(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
02/06	Lecture #12 Distant Supervision [ slides ]	Ratner et al. Snorkel: rapid training data creation with weak supervision
02/08	Lecture #13 Generative adversarial learning [ slides ]	Goodfellow et al., Generative Adversarial Nets
02/10	Lecture #14 Generative adversarial learning [ slides ]	Arjovsky et al., Wasserstein GAN
02/13	Lecture #15 Reinforcement learning [ slides ]	Lilian Weng, A (Long) Peek into Reinforcement Learning
02/15	Lecture #16 Reinforcement learning [ Slides: see Lecture#15 ]	N/A	HW1 due HW2 out
02/17	Lecture #17 Reinforcement learning [ slides ]	Sutton, Barto, Reinforcement Learning, An Introduction, Chapter 13.
02/20	Presidents' Day Holiday (No class)
02/22	Lecture #18 Reinforcement learning [ slides ]		Project mid-term report due
02/24	Lecture #19 Reinforcement learning for text generation [ slides ]	Han et al., Efficient (Soft) Q-Learning for Text Generation with Limited Good Data
02/27	Lecture #20 Reinforcement learning for text generation [ slides ]
03/01	Lecture #21 N/A [ Video recording will be posted later ]
03/03	Lecture #22 Meta learning [ slides ]	Lilian Weng, Meta-Learning: Learning to Learn Fast	HW2 due
03/06	Lecture #23 Meta Learning [ See slides of L#22 ]
03/08	Lecture #24 A `Standard Model' of ML [ slides ]	(Optional) Hu and Xing, Toward A "Standard Model" of Machine Learning
03/10	Lecture #25 A `Standard Model' of ML [ Slides: See L#24 ]
03/13	Lecture #26 A `Standard Model' of ML [ Slides: See L#24 ]
03/15	Final Project Presentation
03/17	Final Project Presentation
Final Week			Project final report due

01/09

Lecture #1:
Overview
[ slides ]

01/11

Lecture #2
ML Basics
[ slides ]