This class is an introductory graduate course in machine learning. The class will briefly cover topics in regression, classification, mixture models, neural networks, deep learning, ensemble methods and structure prediction.

Prerequisites: A good knowledge of statistics, linear algebra and calculus is highly recommended as well as good programming skills.

back to top

  • Apriil 6th: Office hours on Tuesday April 7th 2-3pm, Pratt 290E
  • Apriil 4th: Project deadline extended until April 17th at noon (only if you are not graduating in June)
  • March 20th: Prof. Rich Zemel will have office hours on Wednesday March 25th 4-5pm, Pratt 290D
  • March 18th: The exam will be on March 30th from 12 to 2pm, location GB248
  • March 18th: Office hours today will only be from 4 to 4:30pm
  • March 7th: Every student should submit on CDF the project proposal individually, even if the project selected is one of the suggested ones
  • March 7th: Due to the TA strike, the deadline for A2 has been extended until Thursday March 12 at noon
  • Feb 26th: Click on this link for a document containing explanation of code for A2
  • Feb 26th: The class is now on Piazza, see the following link to register
  • Feb 25th: Projects are out (see link at the end of the page), proposal due March 5th, reports due April 10.
  • Feb 17th: Assignment 2 is out, due March 9. Note that this is a longer assignment!
  • Feb 14th: No Class or tutorial on the week of Feb. 16
  • Feb 9th: Use A1 as the assignment name, and the following command to submit your assignment: submit -c csc2515h -a A1 A1.tar.gz
  • Feb 1st: CDF accounts have been created. For new accounts, students need to activate their account by setting a new password. Any student can lookup their CDF login and set their password anytime by using http://www.cdf.toronto.edu/resources/cdf_account_management.html
  • back to top

    When emailing us, please put CSC2515 in the subject line.

    back to top

    Each student will need to do the homework, exam and complete a project (done individually or in pairs).


    The final grade will consist of the following
    Exam 35%
    Homework (handed at the due date)30%
    Project (proposal, final report)35%

    Project

    Each student will need to write a short project proposal (due March 5th). The projects will be research oriented. The proposal has to be approved by the instructor. By April 10th the final project report (in the form of a paper) will need to be handed in. Additionally, there will be a short, roughly 10 min, presentation.

    The students can work on projects individually or in pairs. The project can be an interesting topic that the student comes up with himself/herself or with the help of the instructor (list of projects available here). The grade will depend on the ideas, how well you present them in the report, how well you position your work in the related literature, how thorough are your experiments and how thoughful are your conclusions.

    back to top

    Click on the syllabus


    back to top

    DateTopicReadingsPresentersSlides
    Jan 5Course Introduction Richard Zemel lecture1
    Jan 12Regression Bishop, Chapter 1.0-1.1; 3.1 Raquel Urtasun lecture2
    Jan 13Review on Probability Tutorial TA: Shenlong Wang tutorial1
    Jan 19Discriminative Classification Bishop: 120-127 , 179-195 Raquel Urtasun lecture3
    Jan 20Optimization Tutorial TA: Shenlong Wang tutorial2
    Jan 26Generative Classification Bishop 4.1.2, 4.3.4, 4.2.2, 380-381 Raquel Urtasun lecture4
    Jan 27Linear Regression and NN Tutorial TA: Ali Punjani tutorial3
    Feb 2Neural Networks Richard Zemel lecture5
    Feb 3Neural Network Examples Tutorial TA: Ali Punjani tutorial4
    Feb 9Clustering, MOG, EM Richard Zemel lecture6
    Feb 10MOG Tutorial TA: Shenlong Wang
    Feb 16NO CLASS
    Feb 17NO TUTORIAL
    Feb 23Continuous Latent Variable Models Alexander Schwing lecture7
    Feb 24PCA Tutorial TA: Ali Punjani tutorial5
    March 2Ensemble Methods Richard Zemel lecture8
    March 9SVMs and kernels Raquel Urtasun lecture9
    March 16Topics: Structured Prediction Raquel Urtasun lecture10
    March 23Topics: Deep Learning Raquel Urtasun lecture11
    March 30EXAM

    back to top

    HW2: (out Feb. 17, due March 9 at 1pm) > HW2 > code

    HW1: Classification & Complexity (out Jan. 26, due Feb 9 at 1pm) > HW1 > code

    back to top

    Project Instructions: (out Feb. 26, due April 10 at noon) > Instructions

    back to top