CSC412/2506 Winter 2020: Probabilistic Learning and Reasoning¶
Overview¶
The language of probability allows us to coherently and automatically account for uncertainty. This course will teach you how to build, fit, and do inference in probabilistic models. These models let us generate novel images and text, find meaningful latent representations of data, take advantage of large unlabeled datasets, and even let us do analogical reasoning automatically. This course will teach the basic building blocks of these models and the computational tools needed to use them.
When, Where, and Who¶
Lectures:
Tutorials:
- CSC412/2506: Thursdays 13:00 - 14:00
Discussion Forum: Requires Invitation
Instructors: David Duvenaud and Jesse Bettencourt
Instructor Email: csc412prof AT cs DOT toronto DOT edu
Instructor Office Hours:
David
Time: Thursdays 15:15 - 16:45
Room: Pratt 384
Jesse
Time: Wednesdays 13:10-14:00
Room: Bahen 2283
Teaching Assistants: Juhan Bae, David Madras,Haoping Xu, and Siham Belgadi
TA Email: csc412tas AT cs DOT toronto DOT edu
TA Office Hours:
Teaching Assistants will hold weekly office hours in BA 2283:
Thursdays: 11:10 - 12:00
Fridays: 14:00 - 15:00
COVID Alternative Schedule¶
- Assignment 0: 10% (Jan 24)
- Midterm: 35% (Feb 11 during lecture)
- Assignment 1: 15% (Feb 24)
- Assignment 2: 20% (Mar 22)
- Assignment 3: 20% (Apr 16)
Final Exam: 30% (TBD)
Course Syllabus¶
Course Information inclduing Schedule, Contact Information, Links to Material, and Policies can be found in the syllabus.
On Lecture Notes¶
Lecture notes included here are works in progress. These were initially typed by John Giorgi as lecture notes for previous course offering. Actual content of lectures may deviate from these notes. However, topics which will be assessed in midterm and final exams will be present in these notes.