CS 294-131: Special Topics in Deep Learning

Instructors

Trevor Darrell

John Canny

Teaching Assistants

Coline Devin

Office Hours

Coline Devin: By appointment

Lectures

Time: Tuesday 12:30-1:59pm

Location: Soda 306

Piazza

Course announcements will be announced through Piazza. If you are in the class, [sign up on Piazza])(https://piazza.com/class/jl5o7zd1s439l).

##Syllabus

Date	Speaker	Readings	Talk
08/28	Nicholas Carlini	Main Reading: https://arxiv.org/pdf/1802.00420.pdf https://arxiv.org/pdf/1802.05666.pdf Background Reading: https://arxiv.org/pdf/1706.06083.pdf https://arxiv.org/pdf/1608.04644.pdf	Video
09/04	Trevor Darrell	Main Reading: https://arxiv.org/abs/1704.05526 Background Reading: https://arxiv.org/abs/1601.01705	Video
09/11	Coline Devin	Main Reading: https://arxiv.org/abs/1708.04225 https://arxiv.org/abs/1609.07088 Background Reading: https://arxiv.org/abs/1509.06113	Video
09/18	Amir Zamir	Main Reading: Taskonomy Time Contrastive Networks Background Reading: https://arxiv.org/abs/1505.05192 https://arxiv.org/abs/1403.6382	Video
09/25	Fisher Yu	Main Reading: Dilated Residual Networks Deep Layer Aggregation Background Reading: Fully Convolutional Networks for Semantic Segmentation Multi-Scale Context Aggregation by Dilated Convolutions	Video>
10/2	Michael Yartsev: Cancelled, replaced by Lisa Hendricks	Main Reading: Background Reading:	Video
10/9	David Dohan and Adams yu	Main Reading: QANet Attention is all you need Background Reading: ELMO Illustrated Transformer	Video
10/16	Lydia Liu	Main Reading: DelayedImpact of Fair Machine Learning Background Reading: Fair prediction with disparate impact Equality of Opportunity in Supervised Learning	Video
10/23	Larry Zitnick	Main Reading: Rich Feature Hierarchies Mask RCNN Background Reading: Deep Residual Learning	Video
10/30	Chris Olah	Main Reading: Feature Visualization Building Blocks of Interpretability Background Reading:	Not yet available
11/06	Richard Zhang	Main Reading: Colorful Image Colorization The Unreasonable Effectiveness of Deep Features as a Perceptual Metric Background Reading: Toward Multimodal Image-to-Image Translation Real-Time User-Guided Image Colorization	Not yet available
11/13	Michael Yartsev	Main Reading: Paper 1 Paper 2 Background Reading: Paper 3 Paper 4	Not yet available
11/20	No Speaker for Thanksgiving Holiday
11/27	Anne Collins	Main Reading: Book Chapter Collins2018_JoCN Background Reading:	Not yet available

Course description

In recent years, deep learning has enabled huge progress in many domains including computer vision, speech, NLP, and robotics. It has become the leading solution for many tasks, from winning the ImageNet competition to winning at Go against a world champion. This class is designed to help students develop a deeper understanding of deep learning and explore new research directions and applications of deep learning. It assumes that students already have a basic understanding of deep learning. In particular, we will explore a selected list of new, cutting-edge topics in deep learning, including new techniques and architectures in deep learning, security and privacy issues in deep learning, recent advances in the theoretical and systems aspects of deep learning, and new application domains of deep learning such as autonomous driving.

Class format and project

This is a lecture, discussion, and project oriented class. Each lecture will focus on one of the topics, including a survey of the state-of-the-art in the area and an in-depth discussion of the topic. Each week, students are expected to complete reading assignments before class and participate actively in class discussion.

Students will also form project groups (two to three people per group) and complete a research-quality class project.

Enrollment information

For undergraduates: Please note that this is a graduate-level class. However, with instructors’ permission, we do allow qualified undergraduate students to be in the class. If you are an undergraduate student and would like to enroll in the class, please fill out this form and come to the first lecture of the class. Qualified undergraduates will be given instructor codes to be allowed to register for the class after the first lecture of the class, subject to space availability.

If you have not received grades for some classes that you are currently enrolled in, please choose Currently Enrolled and then update the form when you receive your final grades. You may also be interested in this class, which is open to undergraduates.

Students may enroll in this class for variable units.

1 unit: Participate in reading assignments.
2 units: Both reading assignments and a project. Projects may fall into one of four categories:
- Distill-like Literature Review of a deep learning topic (e.g., a Distill-like blog post illustrating different optimization techniques used in deep learning)
- Reimplement research code and open source it
- Conference level research project
You may not take this class for 3 or 4 units.

Deadlines

Reading assignment deadlines:
- Submit questions about the reading material by Monday noon.
Project deadlines:
- Project proposal: Friday October 12, 2018, 11:59pm
- Project Milestone: Friday November 16, 2018, 11:59pm
- Final write up: December 10, 2018, 11:59pm
- Project presentations: (Tentative) December 14, 2018

Grading

20% class participation
25% weekly reading assignment
55% project

Additional Notes

For students who need computing resources for the class project, we recommend you to look into AWS educate program for students. You’ll get 100 dollar’s worth of sign up credit. Here’s the link .