CPSC 340 - Machine Learning 2020

General Course Information

  • Lectures (beginning Sept 9th): Mondays, Wednesdays, and Fridays 2-3pm (103) and 4-5pm (101). Online. Find zoom links to lectures in Canvas and in the calendar below.
  • Instructor: Dr. Frank Wood.
  • TA Office hours: Also in the calendar below
  • The generic course webpage has the course synopsis, registration information, prerequisites, textbook recommendations, pre-Covid-19 grading policy, list of topics, and related courses.

COVID-19 grading policy

  • Both the midterm and the final will be “take-home” style involving a written component and a Kaggle contest.
  • Homework will be marked as “complete” or “incomplete” and “obviously cheating” or “actually trying to learn” only.
  • Effectively the course mark will be pass fail. There will be three default marks: A+-100% A=90% D=50%. The instructor retains the right to assign any other mark as well for any reason.

Registration

The course is oversubscribed already. The only way to register for the course is to sign up for the waiting list. For questions about the waiting list policies, see here.

You should sign up for the waiting list even if it is long; a lot of students tend to drop the course. Signing up for the waiting list also makes it more likely that we will open up extra sessions, expand class sizes, or offer additional courses on these topics.

Tutorials

The tutorials are:

  • T1A (Tue 16:30 17:30),
  • T1B (Thu 9:00 10:00),
  • T1C (Thu 10:00 11:00),
  • T1D (Mon 17:00 18:00),
  • T1E (Tue 15:30 16:30),
  • T1F (Thu 11:00 12:00),
  • T1G (Thu 13:00 14:00),
  • T1H (Wed 12:00 13:00),
  • T1K (Mon 13:00 14:00),
Week Date (Monday) TA(s)
1 Sep 07 Ivy (D,H,K), Peyman ( ), Amit ( ), Larry (A,E,G), Mark ( ), Shahriar ( ), Erik (B,C,F), Yancey ( ), Yuxin ( )
2 Sep 14 Ivy ( ), Peyman (A,B,H), Amit ( ), Larry ( ), Mark (D,E,G), Shahriar ( ), Erik ( ), Yancey (F,C,K), Yuxin ( )
3 Sep 21 Ivy ( ), Peyman ( ), Amit (A,B,C), Larry ( ), Mark ( ), Shahriar (D,E,G), Erik ( ), Yancey ( ), Yuxin (F,H,K)
4 Sep 28 Ivy (D,H,K), Peyman ( ), Amit ( ), Larry (A,E,G), Mark ( ), Shahriar ( ), Erik (B,C,F), Yancey ( ), Yuxin ( )
5 Oct 05 Ivy ( ), Peyman (A,B,H), Amit ( ), Larry ( ), Mark (D,E,G), Shahriar ( ), Erik ( ), Yancey (F,C,K), Yuxin ( )
6 Oct 12 Ivy ( ), Peyman ( ), Amit (A,B,C), Larry ( ), Mark ( ), Shahriar (D,E,G), Erik ( ), Yancey ( ), Yuxin (F,H,K)
7 Oct 19 Ivy (D,H,K), Peyman ( ), Amit ( ), Larry (A,E,G), Mark ( ), Shahriar ( ), Erik (B,C,F), Yancey ( ), Yuxin ( )
8 Oct 26 Ivy ( ), Peyman (A,B,H), Amit ( ), Larry ( ), Mark (D,E,G), Shahriar ( ), Erik ( ), Yancey (F,C,K), Yuxin ( )
9 Nov 02 Ivy ( ), Peyman ( ), Amit (A,B,C), Larry ( ), Mark ( ), Shahriar (D,E,G), Erik ( ), Yancey ( ), Yuxin (F,H,K)
10 Nov 09 Ivy (D,H,K), Peyman ( ), Amit ( ), Larry (A,E,G), Mark ( ), Shahriar ( ), Erik (B,C,F), Yancey ( ), Yuxin ( )
11 Nov 16 Ivy ( ), Peyman (A,B,H), Amit ( ), Larry ( ), Mark (D,E,G), Shahriar ( ), Erik ( ), Yancey (F,C,K), Yuxin ( )
12 Nov 23 Ivy ( ), Peyman ( ), Amit (A,B,C), Larry ( ), Mark ( ), Shahriar (D,E,G), Erik ( ), Yancey ( ), Yuxin (F,H,K)
13 Nov 30 Ivy (D,H,K), Peyman ( ), Amit ( ), Larry (A,E,G), Mark ( ), Shahriar ( ), Erik (B,C,F), Yancey ( ), Yuxin ( )

Teaching Assistants (TA)

  • Ivy Qiuhan
  • Peyman Gholami
  • Amit Kadan
  • Larry (Yunpeng) Liu
  • Mark Ma
  • Shahriar Shayesteh
  • Erik Ryhorchuk
  • Yancey Yang
  • Yuxin Zhang

Textbook

There is no required textbook for this class. A introductory book that covers many (but not all) the topics we will discuss is the Artificial Intelligence book of Russell and Norvig (AI:AMA) or the Artificial Intelligence book of Poole and Mackworth (you may need these for other classes). More advanced books include The Elements of Statistical Learning (ESL) by Hastie et al., Murphy’s Machine Learning: A Probabilistic Perspective (ML:APP) which can be accessed through the library here, and Bishop’s Pattern Recognition and Machine Learning (PRML). For books with a bigger focus on data mining, see Introduction to Data Mining (IDM) and Mining of Massive Datasets.