APS360 Fundamentals of AI

Winter 2019

Home
Quercus
Piazza
Assignments
Project
Midterm
Anonymous Feedback

Course Description

A first level machine learning/artificial intelligence software course. The course will focus on learning through implementation of machine learning systems. Students will implement machine learning (specifically deep learning) techniques using Python, Numpy, and PyTorch. Course Information Sheet

All announcements will be made on the course message board.

Course Staff

Instructor: Lisa Zhang
Office Hours: Thursday 3pm-4pm BA2197 (and by appointment)
Email: lczhang [at] cs [dot] toronto [dot] edu
Please include "APS360" in your email subject.

Head Teaching Assistant: Hojjat Salehinejad
Teaching Assistants: Andrew Jung, Bibin Sebastian, Kingsley Chang
TA Office Hours (weeks 2-6): Wednesday 11am-12pm BA2197

Tentative Schedule

The course schedule is tentative, and subject to change.

DateMaterialReadingDeadline
Week 1Jan 7Monday Lecture:
Monday Tutorial:
Thursday Lecture:
  • Software Installation Instructions [pdf]

Lecture Notes:
  • From Pigeons to Neural Networks [html] [ipynb]

Study Questions:
Week 2Jan 14Monday Lecture:
  • Neural Network Terminology [slides]

Monday Tutorial:
Thursday Lecture:
  • Neural Network Training [slides]
Lecture Notes:
Study Questions:
Assignment 1 (Jan 20)
Week 3Jan 21Monday Lecture:
Monday Tutorial:
  • Assignment 2 Walkthrough

Thursday Lecture:
  • Convolutional Neural Networks (CNN) [slides]
Lecture Notes:
Reading:
Advanced:
Just For Fun:
Study Questions:
Assignment 2 (Jan 27)
Week 4Jan 28Monday Lecture and Tutorial Cancelled Due to Snow Storm

Thursday Lecture:
  • Regularization; CNN Architectures [slides]
Lecture Notes:
Reading:
Study Questions:
Week 5Feb 4Monday Lecture:
Monday Tutorial:
  • Assignment 3 Data Collection [pdf]

Thursday Lecture:
  • Project
  • Unsupervised Learning and word2vec [slides]
Lecture Notes:
Reading:
Study Questions:
Assignment 3 Part 1 (Feb 4)

Assignment 3 Part 2 (Feb 10)
Week 6Feb 11Monday Lecture:
  • GloVe and Sentiment Analysis [slides]

Monday Tutorial:
  • Assignment 4 Walkthrough

Thursday Lecture:
  • Recurrent Neural Networks [slides]
Lecture Notes:
Reading:
Study Questions:
Assignment 4 (Feb 17)

Reading week, no class / tutorial

Project Proposal (Feb 24)
Week 7Feb 25Monday Lecture-turned-tutorial:
  • Assignment 5 Walkthrough
  • Midterm [pdf]
  • Practice Midterm Notes [pdf]

Thursday Lecture:
  • Midterm (in room RW117)
Assignment 5 (March 10)
Week 8Mar 4Monday Lecture:
Monday Tutorial:
  • Midterm Takeup

Thursday Lecture:
  • Text Generation use Recurrent Neural Networks [slides]
Lecture Notes:
  • Text Generation using Recurrent Neural Networks [html] [ipynb]

Study Questions:
Reading:
Progress Meeting (Mar 4-11)
Week 9Mar 11Monday Lecture:
Monday Tutorial:
  • Project Progress Report [slides]

Thursday Lecture:
  • Reinforcement Learning [slides]
Study Questions: Progress Report (Mar 17)
Week 10Mar 18Monday Lecture:
Monday Tutorial:
  • Project

Thursday Lecture:
  • Generative Adversarial Networks [slides]
Lecture Notes:
  • Generative Adversarial Networks [html] [ipynb]

Study Questions:
Week 11Mar 25Monday Lecture:
  • Fairness in AI

Monday Tutorial:
  • Presentation Skills

Thursday Lecture:
  • Ethics in AI
Presentation Slides (Mar 29)
Week 12Apr 1Project Presentations
  • Monday, April 1: BA1210
  • Thursday, April 4: BA1200
Project Report (Apr 5)

Exams