A picture of my smiling mug

David J. Finton

finton@cs.wisc.edu Computer Sciences Department University of Wisconsin-Madison 1210 West Dayton Street Madison, WI 53706 (608) 262-9275


Welcome to my page! I'm a grad student / research nerd in artificial intelligence here at the University of Wisconsin-Madison. I grew up in Grand Rapids, Michigan, (which is the Late Show's ex-Home Office), earned a degree in math at Michigan State, and a master's in computer science here at the UW. I'm now a dissertator at this institution, after taking a little over a year to develop traffic measurements software for AT&T after my first thesis advisor left Wisconsin. When I'm not at my trusty NeXTstation or the library, I enjoy playing trumpet and piano, listening to "longhair music", playing volleyball with the InterVarsity folks, and contributing to the SuperSoaker arms race.

If you have any comments about my pages, feel free to use my comment form, or just send me e-mail. Or finger my account to see my current plan and whether I'm on the system.

Gainful employment:

I am a TA for CS 540, Introduction to Artificial Intelligence.

Current Project:

If computers are so smart, why do we have to understand them? Making machines more intelligent is the goal of Artificial Intelligence. To me, the essence of intelligence is the ability to learn and adapt, to learn to act appropriately in order to reach our goals. Reinforcement learning treats this problem in the general case where the system has outputs to control actions that can change its environment, and it has inputs through which it senses its environment. It also has an input for reinforcement, which is a weak kind of feedback which can be expressed as a positive or negative number. So, instead of having a teacher to present the system with input/output pairs, the system instead receives "thumbs up" or "thumbs down" at irregular intervals.

My work has focussed on how the need to distinguish good actions from bad ones can direct the process of building a good representation of the environment in terms of relevant, or important features. (See my note on importance-based feature extraction). Currently I am applying this notion of importance to the problem of learning to balance the need to explore the world with the need to perform optimally (exploration vs. exploitation). I am also investigating ways of using importance to make the learning process more efficient by allowing the system to specify the starting points for its learning experiments (active learning). My goal is to develop a better understanding of intelligent adaptation. I hope that this will provide a basis for intelligent action which will also benefit from knowledge-based and task-based work. See my (really out-of-date, sorry!) reinforcement learning page for more information.

My Hotlist

This is my browser-independent hotlist. I keep a copy here so I can access it from any of the browser/platform combinations I use. It's actually my Bookmarks file from OmniWeb, which is a more elegant and more functional browser than Netscape, in my opinion. OmniWeb is currently only available for NEXTSTEP, but will be available for all the OpenStep variants when OpenStep is released.

My Editorial Pages:

Wisconsin Sites:

Some of My Favorite Places to Visit:

And now, a word from my sponsor.


Last modified: October 31, 1996
finton@cs.wisc.edu