CS760: Machine Learning Related Info


Irene M. Ong
CS760 Teaching Assistant
Office Hours: Monday and Friday from 11:30am - 12:30pm and by appointment (send email)
1309 Computer Sciences Department
University of Wisconsin
1210 W. Dayton St.
Madison, WI 53706
ong@cs.wisc.edu

Class Lecture Notes

Class Project:
  1. Datasets
  2. Professor Shavlik will be reading your project reports so you might want to be thorough when you present, justify, compare and analyze your work.
Homework 4:Tips
  1. The difference between SARSA and Q-learning.
  2. Don't forget to dynamically adjust the learning rates (alpha and eta).
  3. Note: HW4 grade "will be based on system design, justification, and analysis. Be sure to carefully present and analyze your experimental results, especially comparing your three approaches."
Homework 3:Tips
  1. Notes on ROC curve: ML Algorithm output == difference between output node0 and output node1 (i.e. probability of correct prediction) and Correct category == does actual output agree with predicted output?
Homework 2:Tips
  1. Start early!
  2. Design your data structure for d-trees with boosting in mind.
  3. Make sure you include everything that was requested by HW2 in your report.
  4. Dietterich paper (pdf) | postscript version (with clearer print of the algorithm)
Homework 1:Tips
  1. Don't forget to describe and justify everything that was requested by Homework 1 in your report.
  2. When printing out your code to turn in, use the command "enscript -2rG -P<printername> <filename>"
Homework 0: Supplementary material
  1. Note that the main points of this assignment are (i) creating your dataset and (ii) writing a robust parser to read in your dataset once it is in the required format. Make sure your parser can handle any number of whitespace (this includes tabs, carriage returns, etc), report illegal values, etc.
  2. Here is an example Makefile.
  3. Links to datasets (please send me links to other datasets that you may find)
Please feel free to email me or stop by at my office hours if you encounter any problems with any homework.


I am a fourth year graduate student in the Department of Computer Sciences at the University of Wisconsin-Madison. I graduated from Cornell University with a B.A. in Computer Science and Biology, and received my MS in CS at UW in 2001.

I took CS760 with Prof. Shavlik in the Spring of 2001. This is my first TA assignment at UW, although I have had some previous teaching experience including teaching upper level undergraduate students in the Summer Research Program in Biostatistics (SRPB).

My research interests lies in data mining, particularly Bayesian statistical methods, machine learning and inductive logic programming with applications to biological and medical data. I am particularly interested in gene expression analysis and biological networks. I am working with Professor David Page on ways to infer how genes regulate other sets of genes in the bacterium E.coli from time series gene expression array data.

Back to CS760.