Thursday, June 28, 2007

Manifesto for a Material Study of Learning

Continuing in the vein of "winding down the school year" the EES met on June 26 (there was a BBQ on Sunday so we rescheduled) to talk about a 24 page final paper, written by Anna, full of [insert better example than this here] notes that was dense enough to expand into a book if it's not broken into six papers instead :-)

The abstract:

I propose a program for seeking thick, data-rich analogies between learning systems. The goal is to understand why evolution is able to design species; why animals are able to acquire useful behavior patterns; and why communities of scientists are able to find predictively useful theories. Each individual system is already being studied by a large number of system-specific specialists. My proposal offers a framework for enrolling these system-specific research efforts into a single, larger endeavor.

Specifically, I argue that each of the above systems can be understood as a procedure of natural selection undertaken on a certain kind of fitness landscape with a certain kind of variation-making. I argue that if we make the fitness landscape and variation-making central objects of study, we will be able to move past the thin cross-system models that have previously been offered to make rich contact with the data.

Having talked about the paper, the abstract appears especially abstract relative to the content of the paper. For example, there's no mention in the abstract of the No Free Lunch Theorem or Occam's Razor or Grue or...

No comments: