The goal of the exercise is to put everyone on the same page as far as
ability to run MATLAB and have the basic machine learning toolbox that we'll
use/upgrade during the semester. So, you should:

1) try to get MATLAB running on whatever platform you're comfortable with,
preferably on the computer where you'll be doing your assignments/project.
Don't hesitate to ask your peers, CNS, Caroline, and me for help (in that
order :-). The newsgroup is an excellent venue for that, as well, and I'll
read that regularly.

2) Install the machine learning toolbox. The toolbox is available as
http://www.cc.gatech.edu/classes/AY2002/cs4640_spring/toolbox.tar.gz
Just decompress the directory structure to a random place and add the 5
directories ml,aml,util,clusters, and mldemo to your MATLAB path.

3) run the script MLInit (in toolbox/mldemo) to initialize the demos
(provides some training data)

4) run the script mlfig04 (in toolbox/mldemo) and print out the plot it
prints.

5) **optional**: read the file toolbox/ml/README and try to figure out what
is happening. Since we have not covered this yet in the lectures, it would
be just curiosity on your part, which is encouraged.

As said in class, grading exercises is pass/fail, and the hand-in is due to
Caroline at the beginning of class on Tuesday Jan 15. The grading is easy:
if you turn in a plot on Tuesday, you pass, fail otherwise. If you can't get
MATLAB to run on your own computer, try and make do with a CoC machine. I
know it works on Linux, e.g. helsinki.cc.gatech.edu.