Assignments

Due dates

• All assignments 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 be graded out of 6, 4, 2 or 0 depending on whether they are 1, 2, 3 or more days late. 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 will involve using variations of the basic backpropagation algorithm to improve generalization.

• Assignment 3 will involve learning a mixture of Gaussians.

• Assignment 4 will involve 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 will involve learning a Restricted Boltzmann Machine.

A cork board is installed to display information and notices about the CDF computing facility that will be 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/