Machine Learning (ML) is, with no doubt, one of the most important aspects of artificial intelligence and has enjoyed great success in various domains. In this course, we will cover basics of ML. Notably, this edition of the course will be much easier than the previous edition. The previous edition focuses on statistical learning theory and is pretty mathy. This edition is still mathy, but much less than the previous.

Logistics

  • Instructor: Shangtong Zhang
  • TA: Shuze Liu
  • Location: Rice Hall 340
  • Time: Tuesday & Thursday, 9:30 - 10:45
  • Office Hours:
    • Shangtong: Tuesday & Thursday, 10:45 - 11:15 (Rice Hall 422)
    • Shuze: Monday, 15:30 - 16:30, Zoom with in-person meetings upon request
  • UVACanvas: 25S CS6316 Machine Learning
  • Prerequisite:
    • (Basics of) Probability, Linear Algebra, Calculus, and Python
  • Undergraduates: I am in general not against undergraduates taking this course. If you are a UVA undergraduate and believe you fulfill all the prerequisites and the textbook seems interesting and readable to you, please move forward directly by submitting the proper forms, assuming I will approve it. All the information I have about this course is available on this website, so please exercise your judgment. Different schools and colleges have different required forms. It is your responsibility to figure out which form to submit and where to submit it - this is another hidden prerequisite for this course. Due to the giant amount of forms I receive, I am not able to check the status of individual forms. If you believe one form should have been signed, just send it again. The classroom Rice 340 has reached its capacity of 38 students according to the fire code. At the moment only the fire department is able to overwrite this and I cannot enrol students even manually. 

Teaching

  • Textbook: We will follow the Pattern Recognition and Machine Learning (PRML) textbook. We aim to cover all chapters of the textbook. So we will move forward roughly with 1 chapter per week.
  • Lectures: All lectures are whiteboards. To encourage attendance, there will be no slides or notes. But I am sure you can find everything in PRML. As a courtesy, I will try my best to record each lecture (though not guaranteed) and post the recordings via email. That being said, it might be good to factor this whiteboard format into consideration when enrolling in this course.

Roadmap

You are expected to read each chapter for each week.

  • Week of Jan 13: Chapter 1
  • Week of Jan 20: Chapter 2
  • Week of Jan 27: Chapter 3
  • Week of Feb 3: Chapter 4
    • HW1: Figures 1.4, 1.5
  • Week of Feb 10: Chapter 5
    • HW2: Figures 3.5, 3.6
  • Week of Feb 17: Chapter 6
    • HW3: Exercises 4.13, 4.17
  • Week of Feb 24: Chapter 7
    • HW4: Exercises 5.2, 5.5
  • Week of Mar 3: Chapter 8
    • HW5: TBA
  • Week of Mar 10: Spring recess, no course
    • HW6: TBA
  • Week of Mar 17: Chapter 9
    • HW7: TBA
  • Week of Mar 24: Chapter 10
    • HW8: TBA
  • Week of Mar 31: Chapter 11
    • HW9: TBA
  • Week of Apr 7: Chapter 12
    • HW10: TBA
  • Week of Apr 14: Chapter 13
    • HW11: TBA
  • Week of Apr 21: Chapter 14
    • HW12: TBA
  • Apr 29: Last lecture
    • HW13: TBA

Grading

There are 13 assignments and each assignment has 8 points. So 104 points in total. I will use the standard scheme to translate the points into letter grades and will curve if necessary. There is no exam and no project. The assignments are the only way to gain points. The deadline for each assignment is 11:59pm Sunday. For example, the deadline of HW1 is 11:59pm Feb 9.

The assignment can be either to reproduce figures or to solve exercises.

  • For figure assignments, you need to upload a single Jupyter Notebook file (.ipynb) containing the generated figures and the code. The code needs to be executable.
  • For exercise assignments, you need to upload a single PDF file containing your solutions. The PDF file must be generated by LaTex.

Late Policies

Each assignment has an 8-hour graceful period without any penalty. For example, the latest time to submit HW1 without any penalty is 7:59am Feb 10. If you need extensions for career development purposes (e.g., attending a conference, preparing an important interview), you need to email me one week before the homework deadline. Everyone has a single chance for an 1-week late submission without any penalty (note that this cannot be used for HW13). No other hindsight extension is possible unless doctor notes or SDAC notifications are provided.