Assignments

Due dates

All assignments EXCEPT ASSIGNMENT 4, will be due on Tuesdays at the start of class.
Assignments will be posted on this web page one week before they are due.

Marking scheme and lateness penalties

Each of the 5 assignments will be worth 8% of the final grade.
Except in the case of an official Student Medical Certificate, assignments that are submitted late will have their score reduced by 25% of the maximum achievable score per day (so after 4 days they will get zero however good they are). The time past the deadline will be rounded UP to an integer number of days.

Collaboration Policy for Assignments

You are expected to work on the assignments by yourself. You should not discuss them with anyone except the tutors or the instructor. The report you hand in should be entirely your own work.

What will be in the assignments

A typical assignment will require you to modify and use some Matlab code that implements a simple version of a learning procedure that has recently been covered in the course. You will have to submit a very brief report (one page plus figures) that describes the results you obtained.
Assignment 1 will involve using the backpropagation algorithm to learn to recognize patterns.
Assignment 2 (this has been debugged: you can grab it now) will involve using variations of the basic backpropagation algorithm to improve generalization.
Assignment 3 involves learning a mixture of Gaussians.
Assignment 4 involves learning a Hidden Markov Model.

For your amusement: Some text generated by a 100 state HMM trained on English
For your further amusement: Some text generated by a 100 state HMM trained on accentless French
Assignment 5 involves learning Restricted Boltzmann Machines.

TA for help with CDF machines
THIS WAS FOR LAST YEAR. I do not yet know if it applies for 2008.
We are pleased to announce a CDF Teaching Assistant will be available this term. This TA is for all the courses and is not there to help with the assignments. The purpose of the CDF TA is to assist students in using CDF workstations, and connecting to CDF from laptops and from offsite computers. Optional tutorials will be scheduled on topics related to use of CDF with details posted as soon as they're available. This term's CDF TA is Lucas Lochovsky. Feel free to ask him questions about using CDF during CDF TA hours.

Tentative CDF TA hours will be in BA2210, at computer b2210-25 as follows:
Tuesdays 3:00pm - 5:00pm
Wednesdays 3:00pm - 4:00pm
Thursdays 3:0opm - 5:00pm
The computer b2210-25 will be reserved for the CDF TA during CDF TA hours.

A cork board is installed to display information and notices useful to students. The cork board is located in BA2210, by the computer b2210-25. Please note the cork board will only display CDF stamp approved postings. All other postings will be removed. Please check the cork board for helpful information and notices.

CSC321 - Computation In Neural Networks: || www.cs.toronto.edu/~hinton/csc321/