Course information

Instructors: Roger Grosse and Nitish Srivastava
Section 1: lecture Tues/Thurs 1:10-2pm, tutorial Thurs 12:10-1pm, in BA1200
Section 2: lecture Tues 6:10-7:50pm, tutorial Tues 8:20-9pm, in BA1220

Instructor email: csc321prof[at sign]
TA email: csc321ta[at sign]

Machine learning is a powerful set of techniques that allow computers to learn from data rather than having a human expert program a behavior by hand. Neural networks are a class of machine learning algorithm originally inspired by the brain, but which have recently have seen a lot of success at practical applications. They’re at the heart of production systems at companies like Google and Facebook for face recognition, speech-to-text, and language understanding.

Here are some neat examples of neural net systems developed here at U of T.

This course gives an overview of both the foundational ideas and the recent advances in neural net algorithms. Roughly the first 2/3 of the course focuses on supervised learning — training the network to produce a specified behavior when one has lots of labeled examples of that behavior. The last 1/3 focuses on unsupervised learning — the correct behavior isn’t specified by hand, but the goal is to discover interesting regularities in the data.

The course will be taught as an “inverted classroom,” using the lectures produced by Geoff Hinton several years ago. You will watch the lectures at home, and then we will discuss the material and work through examples during class. You can access the videos, quizzes, and forum on the Coursera web site for the course. You need to log in using your UTorID.

For more details on how the course is organized, please read the course information.