Lecture times and location

• Mondays 15:30-16:20, Wednesdays 15:30-17:20, 3520 West Mall Centre

Instructor

• Mo Chen
  SFU Burnaby, TASC 1 8225
  mochen@cs.sfu.ca
  Office hours: Before and after lectures, Mondays 9:30

Teaching Assistants

• Vishal Batvia,vbatvia@sfu.ca
  Office hours: Tuesday 10:30-11:30 ASB9814

• Dorsa Dadjoo, ddadjoo@sfu.ca
  Office hours: Thursdays 15:00-16:00 ASB9810

• Ghazal Saheb Jam, gsahebja@sfu.ca
  Office hours: Thursdays 12:30 - 13:30 ASB9810

Piazza Online discussion forum

• Sign up link
• Main page

Schedule / Lecture notes

• Jan. 8: 1 Introduction
• Jan. 13: 2 Linear Models for Regression
• Jan. 20: 3 Linear Models for Classification
• Jan. 27: 4 5 Neural Networks
• Feb. 10: 6 Graphical Models I
• Feb. 24: 7 Graphical Models II
• Mar. 2: 8 Sequential Data I
• Mar. 9: 9 Sequential Data II
• Mar. 16: 10 Recurrent Neural Networks
• Mar. 18: 11 Reinforcement Learning | RL with Tensorflow Tutorial | RL TensorFlow Video Tutorial
• Mar. 30: Guest Lectures
• Apr. 8: Final Exam

• Lecture notes adapted from Greg Mori

Assignments

• Assignment 1: Due Feb. 7 Solution1
• Assignment 2: Due Mar. 6 Solution 2
• Assignment 3: Due Apr. 3 Solution 3

Project

• Form groups of 3 to 5 members
• Wonderful project guidelines from Greg Mori, CMPT 419/726 Fall '19

Project options

• Reproduce the results of 3-5 papers (1 paper per group member) in an area covered in this course, and suggest or make improvements, and connect them to a common theme
• Mini Research project related to an area covered in this course.
• Other: please consult with the instructor

Project timeline

• Consultation throughout the term in office hours
• Proposal (1 page maximum, no abstract) Due Feb. 17 | Template
• Poster session: on Canvas, starting Apr. 16 | Template
• Project report (7 pages maximum) due Apr. 20 | Template

Past projects

• ARG (Age Race Gender) Detection Using Transfer learning based on FaceNet Pretrained Model: Report
• Movement Prediction of Three Bouncing Balls: Poster | Report
• Face sketch generation using Generative Attentional Networks: Poster | Report
• Improving Visual Question Answering Using Semantic Analysis and Active Learning: Poster | Report
• Paraphrase Extraction with Neural Machine Translation: Poster | Report
• Semi-Supervised Learning Using GAN: Poster | Report
• Where and When Counts: Action Recognition in Videos: Report
• Leveraging Adversarial training for Monocular Depth Estimation: Poster | Report
• More projects from Stanford CS231n for inspiration

Calendar Objective/Description

Machine Learning is the study of computer algorithms that improve automatically through experience. It provides students who conduct research in machine learning, or use it in their research, with a grounding in both the theoretical justification for and practical application of, machine learning algorithms. Covers techniques in supervised and unsupervised learning, the graphical model formalism, and algorithms for combining models. Students who have taken CMPT 882 (Machine Learning) in 2007 or earlier may not take CMPT 726 for further credit.

Instructor's Objectives

Machine Learning is the study of computer algorithms that improve automatically through experience. Machine learning algorithms play an important role in industrial applications and commercial data analysis. The goal of this course is to present students with both the theoretical justification for and practical application of, machine learning algorithms. Students in the course will gain hands-on experience with major machine learning tools and their applications to real-world data sets. This course will cover techniques in supervised and unsupervised learning, neural networks / deep learning, the graphical model formalism, and algorithms for combining models. This course is intended for graduate students who are interested in machine learning or who conduct research in fields that use machine learning, such as computer vision, natural language processing, data mining, bioinformatics, and robotics. No previous knowledge of pattern recognition or machine learning concepts is assumed, but students are expected to have or obtain, background knowledge in mathematics and statistics.

Prerequisites

None. Students are responsible for catching up on any necessary mathematics background such as linear algebra and calculus.

Grading

• Homework: 30%
• Final Exam: 30%
• Final Project: 40%

All assignments are to be done individually.

Academic Honesty Statement

Academic honesty plays a key role in our efforts to maintain a high standard of academic excellence and integrity. Students are advised that ALL acts of intellectual dishonesty will be handled in accordance with the SFU Academic Honesty and Student Conduct Policies ( http://www.sfu.ca/policies/gazette/student.html ).