Homework Assignments

There will be two homework assignments in the first part of the class: one on self-organizing maps, and another one on backpropagation. These topics were selected because they are the most popular neural network architectures to date.

The assignments have two goals: (1) to obtain deeper understanding on how these architectures work and what their limitations are, and (2) to obtain practical experience in running these algorithms and to become familiar with the simulation programs, so that you can easily get started on the simulations for your project.

The assignments are somewhat open-ended in that you can spend quite a bit of time exploring the variations of the algorithms and different training regimes etc. The point is not to just get them done with miminal effort to get a good grade in the class, but to use the assignments as a starting point for in-depth exploration. You'll get more out of the assignments if you put more effort into them.

The assignments are turned in electronically to the TA using the turnin program before midnight on the day they are due.


risto@cs.utexas.edu
Wed Aug 26 12:17:32 CDT 2009