Special Topics in AI: Deep Learning

CS839, Fall 2020
Department of Computer Sciences
University of Wisconsin–Madison


Course Info

  • Time: TR 4:00PM - 5:15PM
  • Location: BlackBoard Collaborate (see Log in instruction: https://it.wisc.edu/services/web-conferencing)
  • Instructor: Sharon Li
  • Instructor Email: sharonli@cs.wisc.edu
  • Instructor Office Hours: Thursday 5:15-6:15pm
  • TA Office Location: BlackBoard
  • TA: Yiyou Sun
  • TA Email: sunyiyou@cs.wisc.edu
  • TA Office Hours: Tuesday 3-4pm
  • TA Office Location: BlackBoard "TA Room"
  • Piazza Webpage (for discussion and notification): piazza.com/wisc/fall2020/cs839/home, passcode: deeplearning

Note: for emails, please put [CS839] in the subject title. Thanks!

Course Description

In recent years, deep learning has enabled huge progress in many domains including computer vision, speech, NLP, and robotics. This class is designed to help students develop a deeper understanding of deep learning and explore new research directions and applications of AI/deep learning. The course goes in depth on cutting-edge topics within deep learning and their applications, including recent advances in neural architecture design, robustness and reliability of neural networks under adversarial and anomalous attack, learning with less supervision, deep generative modeling, theoretical understanding of deep learning, as well as explaining black-box deep learning models to enhance their transparency. It assumes that students already have a basic understanding of deep learning.

Prerequisites

CS 540: Introduction to Artificial Intelligence, CS 760 Machine Learning, CS 761 Mathematical Foundations of Machine Learning. Familiarity with linear algebra, statistics, optimization is expected. Enrollment is limited to MS/PhD students.

Grading

The grading for the course will be be based on the following. There will be no midterm or final exams.

  • In-class quizzes: 10% (you can skip up to 2 of them)
  • Paper presentation: 20%
  • Project proposal: 10%
  • Final project presentation: 15%
  • Final project report (written): 45%

The following policies are adapted from Mark Craven's CS760 Fall 2016 Course and David Page's CS760 Spring 2018 Course.

Project policies

Projects should be done in groups of 2-4 people. We encourage students to find projects that relate to their ongoing research.

Please email the project proposal to the TA by the proposal deadline. Each group submits only one proposal. The project proposal should include names of the students in the group, the research topic and problem, a brief description of tentative plan for the project. The project report will be due (pdf report and submission of any code written) to the TA by email, by the project deadline. Late days cannot be used for the project because it needs time to grade them all by the end of the exam week, in order to compute final grades on time. Deadlines will be posted on Canvas (but please submit the proposal and the final report to the TA rather than on Canvas).

The basis for the project grade will be your written report and presentation. In particular, grading will NOT take into account the number of students in the group and depend only on the final outcome of the project. The same grade will be given to the members in the group. The report should be in the style of a conference paper (e.g., using the style files of ICML'20), providing an introduction/motivation, discussion of related work, a description of your work that is detailed enough that the work could be replicated, and a conclusion. The format of the description of your work will depend on the nature of your project. If it is an algorithm-based project, then the description should make clear the algorithm(s) implemented and provide experimental results. If it is an application project, the description should say which system was used, how the data (or any other materials used) were collected, what experimental methodology was employed, and some estimate of the quality of the experimental results (e.g. a 10-fold cross-validation accuracy estimate). If it is a theoretical project, then the project description should consist of detailed definitions, theorems, and proofs. Evaluation of the project report will be similar to reviewing a conference/journal paper. See here for reviewing guidelines of a machine learning conference that describe well what we regard as great research outcomes.

Here is a great guide by Kayvon Fatahalian on how to give an effective academic talk. Please follow the tips when preparing for the paper presentation and final project presentation.