General information

Course Logistics

• Instructor:
  Simon S. Du
• Teaching Assistant:
  Yancheng Liang, Siting Li, Yiping Wang
  
• Lecture time and place: Tuesday, Thursday 11:30 -- 12:50 PM, CSE2 G01 or Zoom (see lecture schedule)
• Office Hours:
Simon S. Du: Tuesday 10:00 - 11:00 AM in person (Gates 312)
Yancheng Liang: Wednesday 13:00 -- 14:00 PM on Zoom
Siting Li: Tuesday 16:00 - 17:00 PM in person (Gates 151)
Yiping Wang: Wednesday 16:00 - 17:00 PM in person (Gates 151)
Zoom links are on Canvas

• Ed Discussion

  About the Course, Prerequisites and Grading

  Deep learning is a broad class of machine learning methods based on neural networks, has become the central paradigm of machine learning. This course aims to introduce recent and exciting developments in deep learning. The focus is on the algorithmic and theoretical aspects of deep learning.

  Prerequisites: This is an advanced graduate course, designed for Ph.D. level students, and will assume a substantial degree of mathematical maturity. Students entering the class should be comfortable with programming and should have a working knowledge of linear algebra (MATH 308), vector calculus (MATH 126), probability and statistics (CSE 312/STAT390), algorithms, and machine learning (CSE 446/546).

  Grading: Your grade will be based on 2 homework assignments: HW1 (20%), HW2 (20%), a project proposal (5%), a project presentation (20%), and a final project report (35%)

  Homework

• There are two homework, which will be released on Canvas.
• You have two late days.
• Homework must be typed. You can use any typesetting software you wish (latex, markdown, ms word, etc).
• You may discuss assignments with others, but you must write down the solutions by yourself.
• We follow the standard UW CSE policy for academic integrity.
• Tentative timeline:
• First homework release: October 10th. First homework due: October 24th.
• Second homework release: October 24th. Second homework due: November 7th.

Course project

Projects should be done in groups of 2-4, with the intention of exploring one direction in greater detail. You can use Ed Discussion to form a group. The projects can be either a literature review or original research. For literature review, you do not need to reimplement algorithms. We list ideas for a few project topics on Canvas. It is okay to do projects on topic not listed.
• Timeline:
• Proposal (due date: October 10th): submit a short report (1 - 1.5 pages) stating the papers you plan to survey or the research problems that you plan to work on. Describe why they are interesting and provide a list of appropriate references. You are encouraged to connect this project with your current research.
• Presentation (December 3th and December 5th): details on Canvas.
• Final report (due data: December 13th): You are expected to submit a written project report (~8pages) describing your findings.
• Format: You must use the NeurIPS Latex format.