APS360 Artificial Intelligence Fundamentals (Summer 2019)

Course Description

A first level course on the engineering of machine learning software. The course will focus on learning through implementing various types of machine learning systems. By the end of the course, students will be able to implement neural networks to perform classification on image, text, and other types of data. Students will also have a high-level understandings of neural network models used to generate images, such as autoencoders and GAN. We will focus on implementations using Python, Numpy, and PyTorch. Course Information Sheet

All announcements will be made on Quercus.

Course Staff

Instructor: Lisa Zhang
Office Hours: Monday 4pm-5pm BA2197 (and by appointment)
Email: lczhang [at] cs [dot] toronto [dot] edu
Please include "APS360" in your email subject.

Teaching Assistants: Andrew Jung, Huan Ling, Farzaneh Mahdisoltani, Jake Snell

Tentative Schedule

The course schedule is tentative, and subject to change.

	Date	Material	Reading	Deadline
Week 1	May 6	Monday Lecture: Introduction Biological and Artificial Neurons Slides Thursday Lecture: From Pigeons to Neural Networks Slides Notebook [ipynb] [viewer] Thursday Lab 1: Python and PyTorch	Resources: Colab Instructions Software Installation Instructions (old) Python and Numpy Tutorial PyTorch Introduction [ipynb] [viewer] Lecture Notes: From Pigeons to Neural Networks [html] [ipynb] Study Question: Week 1 Study Questions	Lab 1 (May 15)
Week 2	May 13	Monday Lecture: Neural Network Terminology Neural Network Training Slides Notebook [ipynb] [viewer] (Lisa is away from May 14-25) Thursday Lecture (Jake): Neural Network Training - Hyperparameters and Validation Set Slides Thursday Lab 2: Cats vs Dogs	Lecture Notes: Neural Network Terminology [html] [ipynb] Neural Network Training [html] [ipynb] Study Question: Week 2 Study Questions	Lab 2 (May 22)
Week 3	May 20	Monday: Victoria Day, No Lecture Thursday Lecture (Jake): Multi-Class Classification Slides Thursday Lab 3(a): Data Collection	Lecture Notes: Classification in PyTorch [html] [ipynb] Reading: Troubleshooting Deep Neural Networks Study Question: Week 3 Study Questions	Lab 3a (May 24)
Week 4	May 27	Monday Lecture: Convolutional Neural Networks Slides Notebook [ipynb] [viewer] Thursday Lecture: Convolutional Architectures and Transfer Learning Slides Thursday Lab 3(b): Gesture Recognition	Lecture Notes: Convolutional Neural Network [html] [ipynb] Reading: A Comprehensive Guide to Convolutional Neural Networks A guide to convolution arithmetic for deep learning, Ch 1-3 (pdf) Just For Fun: Hubel and Wiesel Cat Experiment Study Question: Week 4 Study Questions	Lab 3b (~~Jun 5~~ Jun 9)
Week 5	June 3	Monday Lecture: Regularization Deconvolutions and Autoencoders Slides Thursday Lecture Word Embeddings: word2vec and GloVe Slides Thursday Lab 4: Autoencoders	Lecture Notes: Preventing Overfitting [html] [ipynb] Convolution Transpose and Autoencoder [html] [ipynb] Reading: Data Augmentation Word Embeddings Tutorial Recommended: Deconvolution Checkerboard Study Question: Week 5 Study Questions	Lab 4 (~~Jun 12~~ Jun 16)
Week 6	June 10	Monday Lecture: GloVe for Sentiment Analysis Recurrent Neural Networks Slides Thursday Lecture: Recurrent Neural Networks (cont'd) Project Slides	Lecture Notes: Word2Vec and GloVe Embeddings [html] [ipynb] Sentiment Analysis with GloVe Embeddings [html] [ipynb] Recurrent Neural Networks [html] [ipynb] Reading: Representations (up to but excluding "Recursive Neural Networks") Understanding LSTMs (up to but excluding "Step-by-Step LSTM Walk Through") RNN Effectiveness Sentiment Analysis TorchText Study Question: Week 6 Study Questions	Lab 5 (~~Jun 19~~ July 2)
Week 7	Jun 17	Monday Lecture: Midterm Review Thursday Lecture: Midterm (6:10pm-8:00pm in room GB304)		Project Approval (June 21 23)
Reading week, no class				Project Proposal (June 27 30)
Week 8	July 1	Monday: Canada Day, No Lecture Thursday Lecture: Text Generation using Recurrent Neural Networks Slides	Lecture Notes: Text Generation using Recurrent Neural Networks [html] [ipynb] [Colab] CSV Data Download Study Question: Week 8 Study Questions
Week 9	July 8	Monday Lecture: Generative Adversarial Networks Slides Thursday Tutorial: Google Cloud Computational Resources Thursday Lab: Project	Lecture Notes: Generative Adversarial Networks [html] [ipynb] Adversarial Examples [html] [ipynb] Study Question: Week 9 Study Questions	Progress Meetings (July 8-15)
Week 10	July 15	Monday Lecture: Reinforcement Learning Slides Worksheet Thursday Guest Lecture: Prof. Sanja Fidler Thursday Lab: Project	Study Question: Week 10 Study Questions
Week 11	July 22	Monday Lecture: Ethics in AI; Fairness in ML Slides News Articles Adversarial Examples Facial Recognition Database Facial Recognition Opt-Out Google Photos Gorillas Facial Recognition Accuracy Varies by Race Project Maven Sentencing Algorithm Dermatology Fairness DeepNude [contains nsfw images] Thursday Guest Lecture (TBD) Prof. Jason Anderson Thursday Lab: Project	Study Question: Week 11 Study Questions	Progress Report (July 24)
Week 12	July 29	Monday Lecture: Final Term Test Review Slides Thursday: Final Term Test (6pm-8:30pm in room SF3202)
Week 13	Aug 5	Monday: Civic Holiday, No Lecture Thursday: Project (6pm-7pm)		Presentation Slides
Week 14	Aug 12	Monday: Project Presentations (in room BA1200) Thursday: Project Presentations (in room BA1200)		Project Report / Repository (August 15)