All models are wrong, but some are useful -- George Box

Highlights

• Course Schedule
• Reading Guidelines
• Rubrics and Grading Policy
• Honor Code and Other Related Statements

1. Course Information

• Instructor: Yangfeng Ji
• TA: Stephanie Schoch
• Time: Monday and Wednesday, 12:30 – 1:45 PM
• Location: Rice 340
• Office hours:
  • Yangfeng Ji: Thursday 11 AM – 12 PM
  • Stephanie Schoch: By appointment

2. Topics

The goal is to learn machine learning by reading and discussing selected content from several machine learning books and some important machine learning papers. The tentative topics that will be covered in this course

• Bayesian inference
• Probabilistic graphical models
• Variational inference
• Monte Carlo inference
• Variational autoencoders
• Generative adversarial networks
• Other machine learning topics, such as distribution shift, transfer learning and continual learning.

Our lecture schedule can be found here

3. Reading and Discussion Policy

Two important parts of course participation are (1) reading the course materials and (2) participating in class and online discussion.

• Students are required to read the course materials before each lecture, the reading assignment can be found on the reading guideline page.
• Before the lecture, each student should post at least one question about this lecture on the course discussion board.
• After the lecture (within one week), each student should answer at least one question from other students on the discussion board.
• During the class time, the instructor will pick some of the questions for discussion. Students are free to ask further questions during the discussion.

We use Canvas for announcements and discussion. Please let the instructor or the TA know, if you have not received an invitation.

4. Assignments and Grading Policy

The assignments of this course consist of three parts

• Question and discussion
  • Each question assignment: 3.5 points, 35 points in total
  • Each discussion assignment: 4 points, 40 points in total
• Final project
  • Project proposal: 7 points
  • Final project report: 13 points
• Class attendance
  • Total: 5 points

Please refer to the grading policy for grading rubric and additional information.

5. Reference

Textbooks

Our reading assignment will be selected from the following textbooks:

• Bishop. Pattern Recognition and Machine Learning. 2006
• Murphy. Machine Learning: A Probabilistic Perspective. 2012
• Murphy. Probabilistic Machine Learning: Advanced Topics. 2023
• Mackay. Information Theory, Inference, and Learning Algorithms. 2003

Optional

• Please refer to this page for additional readings

6. Related Courses

Many machine learning related courses are offered in Fall 2022.

• Aidong Zhang. CS 6316 Machine Learning
• Tom Fletcher. CS 6501-002 Geometry of Data
• Madhur Behl. CS 6501-005 Learning in Robotics
• Shangtong Zhang. CS 6501-005 Topics in Reinforcement Learning
• Farzad Hassanzadeh. CS 6501-008 Statistical Learning and Graphical Models
• Miaomiao Zhang. CS 6501-010 Machine Learning in Image Analysis
• Felix Lin. CS 6762 Signal Processing, Machine Learning and Control

Updated: 08/21/2022