DSC 291 Machine Learning with Few Labels

Date	Lecture	Suggested Readings	Logistics
04/01	Lecture #1: Overview [ slides ] [ slides ]
04/03	Lecture #2: Overview [ slides/marked: see above ]
04/05	Lecture #3: Overview [ slides ] [ marked ]	Hu and Shu, 2023: Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planning
04/08	Lecture #4: Large Language Model Basics, Self-Supervised Learning [ slides ] [ marked ]	Lecun and Misra, (Blog) Self-supervised learning: The dark matter of intelligence
04/10	Lecture #5: Large Language Model Basics, Self-Supervised Learning [ slides ] [ marked ]	J Eisenstein, Chapter 6 (Language Models)
04/12	Lecture #6: Enhancing Large Language Models [ slides ]	Rich Sutton, The Bitter Lesson
04/15	Lecture #7: Enhancing Large Language Models [ slides ] [ marked ]	Nature article, Lightning talks: science in 5 minutes or less
04/17	Lecture #8: Enhancing Large Language Models [ slides/marked: see above ]
04/19	Lecture #9: Enhancing Large Language Models [ slides ]		Project proposal due ~~HW1 out~~
04/22	Lecture #10: Enhancing Large Language Models [ slides ]	Brownlee, No Free Lunch Theorem for Machine Learning
04/24	Lecture #11: Supervised, Unsupervised Learning [ slides ]	PRML, Chapter 1 (Basic introduction of some ML concepts)
04/26	Lecture #12: Unsupervised Learning: EM Algorithm [ slides ] [ marked ]	PRML, Chapter 9 (Mixture Models and EM)
04/29	Lecture #13: Unsupervised Learning: EM Algorithm [ slides ] [ marked ]
05/01	(No class)
05/03	Lecture #14: Unsupervised Learning: EM, Variational Inference [ slides ] [ marked ] [ recording ]	PRML, Chapter 10.1-10.3 (Variational Inference)
05/06	Lecture #15: Guest Lecture: LM, Grounding, Embodied AI [ slides ] [ recording ]		~~HW1 due~~ HW2 out
05/08	Lecture #16: Variational Inference [ slides ] [ marked ] [ recording ]	PRML, Chapter 10.1-10.3 (Variational Inference)
05/10	(No class)
05/13	Lecture #17: Variational Inference [ slides ]
05/15	Lecture #18: Variational Inference [ slides ]		Project mid-term report due
05/17	Lecture #19: Variational Inference [ slides ]	Deep Learning book, Chap 20.10.3 (Variational Autoencoder) (Optional) Kingma and Welling, 2014, Variational Autoencoders
05/20	Lecture #22:
05/22	Lecture #23:		HW2 due
05/24	Lecture #24:
05/27	Memorial Day observance (No class)
05/29	Lecture #25:
05/31	Lecture #26:
06/03	Lecture #27:
06/05	Lecture #28: Final project presentation
06/07	Lecture #29: Final project presentation
Final Week			Project final report due

04/01

Lecture #1:
Overview
[ slides ] [ slides ]

04/03

Lecture #2:
Overview
[ slides/marked: see above ]

04/05

Lecture #3:
Overview
[ slides ] [ marked ]

Hu and Shu, 2023: Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planning

04/08

Lecture #4:
Large Language Model Basics, Self-Supervised Learning
[ slides ] [ marked ]

Lecun and Misra, (Blog) Self-supervised learning: The dark matter of intelligence

04/10

Lecture #5:
Large Language Model Basics, Self-Supervised Learning
[ slides ] [ marked ]

J Eisenstein, Chapter 6 (Language Models)

04/12

Lecture #6:
Enhancing Large Language Models
[ slides ]

Rich Sutton, The Bitter Lesson

04/15

Lecture #7:
Enhancing Large Language Models
[ slides ] [ marked ]

Nature article, Lightning talks: science in 5 minutes or less

04/17

Lecture #8:
Enhancing Large Language Models [ slides/marked: see above ]

04/19

Lecture #9:
Enhancing Large Language Models
[ slides ]

Project proposal due
~~HW1 out~~

04/22

Lecture #10:
Enhancing Large Language Models
[ slides ]

Brownlee, No Free Lunch Theorem for Machine Learning

04/24

Lecture #11:
Supervised, Unsupervised Learning
[ slides ]

PRML, Chapter 1 (Basic introduction of some ML concepts)

04/26

Lecture #12:
Unsupervised Learning: EM Algorithm
[ slides ] [ marked ]

PRML, Chapter 9 (Mixture Models and EM)

04/29

Lecture #13:
Unsupervised Learning: EM Algorithm
[ slides ] [ marked ]

05/01

(No class)

05/03

Lecture #14:
Unsupervised Learning: EM, Variational Inference
[ slides ] [ marked ]
[ recording ]

PRML, Chapter 10.1-10.3 (Variational Inference)

05/06

Lecture #15:
Guest Lecture: LM, Grounding, Embodied AI
[ slides ] [ recording ]

~~HW1 due~~
HW2 out

05/08

Lecture #16:
Variational Inference
[ slides ] [ marked ]
[ recording ]

PRML, Chapter 10.1-10.3 (Variational Inference)

05/10

(No class)

05/13

Lecture #17:
Variational Inference
[ slides ]

05/15

Lecture #18:
Variational Inference
[ slides ]

Project mid-term report due

05/17

Lecture #19:
Variational Inference
[ slides ]

Deep Learning book, Chap 20.10.3 (Variational Autoencoder)
(Optional) Kingma and Welling, 2014, Variational Autoencoders

05/20

Lecture #22:

05/22

Lecture #23:

HW2 due

05/24

Lecture #24:

05/27

Memorial Day observance (No class)

05/29

Lecture #25:

05/31

Lecture #26:

06/03

Lecture #27:

06/05

Lecture #28:
Final project presentation

06/07

Lecture #29:
Final project presentation

Final Week

Project final report due