Embedded Files
About: This course will cover two areas of deep learning in which labeled data is not required: Deep Generative Models and Self-Supervised Learning. Recent advances in generative models have made it possible to realistically model high-dimensional raw data such as natural images, audio waveforms and text corpora. Strides in self-supervised learning have started to close the gap between supervised representation learning and unsupervised representation learning in terms of fine-tuning to unseen tasks. This course will cover the theoretical foundations of these topics as well as their newly enabled applications.
If you want to peek ahead, this semester's offering will be fairly similar to the previous offering.
Instructors: Pieter Abbeel, Wilson Yan, Kevin Frans, Philipp Wu
Communication:
primary: https://edstem.org/us/courses/53933/discussion/
as needed: cs294-158-staff@lists.berkeley.edu
Lectures: Thursdays 2-5pm (first lecture on 1/18) in 250 Sutardja Dai Hall
Prerequisites: significant experience with probability, optimization, deep learning
Office Hours
Office Hours
For homework, TA office hours are the best venue. For other questions (lecture, final project, research, etc.) any office hours should be great fits.
Pieter: Thursdays 5-6pm (250 Sutardja Dai Hall)
Wilson: Wednesdays 10-11am (Soda Alcove 326)
Kevin: Mondays 10-11am (BWW 1st floor, on the far east side of the building where the white tables are)
Philipp: Tuesdays 10-11am (BWW 1st floor, on the far east side of the building where the white tables are)
Homework (subject to change)
Homework (subject to change)
HW1: Autoregressive Models (out 1/25, due 2/7)
HW2: Latent Variable Models (out 2/8, due 2/21)
HW3: GANs / Implicit Models (out 2/22, due 3/6)
HW4: Diffusion Models (out 3/7, due 3/20)
Final Project
Final Project
See final project page for details.
Main dates:
February 28 Project Proposals
March 8 Approved Project Proposals
April 5 3-page Milestone
May 10 Report and Video Presentation
Tentative Schedule / Syllabus
Tentative Schedule / Syllabus
<<week of 3/25-29, no lecture per Spring Break>>
<<week of 4/22-26, no lecture this week>>
<<week of 4/29-5/3, no lecture per RRR week>>
(5/10) Final Project Reports and Final Project Video Presentations due
(5/10) Final Project Reports and Final Project Video Presentations due
FAQ
FAQ
Q: How do I get into this course?
A: We'll simply follow however the system is set up by the dept/university and let it do its thing
Q: Can undergraduates take this course?
A: This course is targeted towards a PhD level audience. But certainly exceptional undergraduates could be good fits, too.
Q: Is this a real course or a seminar?
A: This is a real course. Instructors will give most of the lectures. There will be substantial homework. There will be a midterm. There will be a substantial final project.
Q: I already want to start learning now, what can I do?
A: You could take a look at the previous offering: https://sites.google.com/view/berkeley-cs294-158-sp20/home
Google Sites
Report abuse