COSC 288: Introduction to Machine Learning

Project 4
Spring 2009

Due: Wed, Apr 8 @ 10 P.M.
13 points

Implement either Zurada's or Mitchell's back-propagation algorithm for multilayer, feed-forward neural networks. Your implementation should include a routine to convert nominal attributes into a binary or linear encoding scheme. Use the bikes, xor, and lenses data sets to evaluate your implementation. The implementation must be general.

Implement the learner as a single executable. No windows. No menus. No prompts. Just do it.

The logic of the implementation should be the same as that for the implementations of p2 and p3.

Your object-oriented design should be something that only a software engineer would love, appreciate, and cherish.

If you happen to have some time on Roadrunner or BlueGene or you just want to run something for a really long time, then you might try using votes and mushroom to evaluate your implementation. I would highly recommend not using ten-fold or even any-fold for these data sets. Try it and you'll see. If you kick off any big job on seva, please be mindful of other users, especially those who use a heavy editor like emacs. Run your process with nice. For example, in tcsh, 

seva% nice nn -t mushroom.tr.mff -T mushroom.te.mff < /dev/null >&! nn.out &
seva% nice java NN -t mushroom.tr.mff -T mushroom.te.mff < /dev/null >&! nn.out &
Note that the fancy redirects prevent ssh from hanging when you log out. The final ampersand puts the job in to the background, where it will run for a long time, and so you can log out and leave the lab.

Instructions for Submission

In the header comments in at least the main file of your project, provide the following information: 
//
// Name
// E-mail Address
// Platform: Windows, MacOS, Linux, Solaris, etc.
// Language/Environment: gcc, g++, java, g77, ruby, python, haskell, etc.
//
// In accordance with the class policies and Georgetown's Honor Code,
// I certify that, with the exceptions of the class resources and those
// items noted below, I have neither given nor received any assistance
// on this project.
//
Make sure I have clear instructions on how to run your executables. If you're using C or C++, then provide a Makefile.

Submit via Blackboard. When you are ready to submit your program for grading, create a compressed archive of a directory containing only your project's source, and upload it to Blackboard. The directory's name should be the same as your net ID. If you need to include a note with your submission, put the note in a README file in the directory.

For example, assume your net ID is ab123. If the directory p3 contains your project, then rename the directory to ab123.

To make the archive smaller, remove any object files, such as .class, a.out, and .o files.

Use zip, tar, or jar to create an archive: 

% zip -r ab123.zip ab123/*
% tar -cf ab123.tar ab123
% jar -cf ab123.jar ab123
Use jar only for Java projects. If you use jar or tar, then compress the archive by typing 
% gzip ab123.tar
% gzip ab123.jar
which creates a file ab123.tar.gz and ab123.jar.gz, respectively.

Upload the compressed archive to Blackboard.

Submit your project before 10:00 P.M. on the due date.