Friday, July 27, 2007

Three stopping points

(i) The ability process ambiguous, confusing, isolated cues into a meaningful, coherent, situation.

This is what FARG already does now. It's what CAPYBLANCA does. But we want to replicate these, using a single framework, at least in NUMBO and Copycat.

(ii) The ability to do it again, now faster

How can the system self-adjust such that, in the future, things get more and more efficient? One idea here that goes beyond FARG is that of (positive or negative) feedback changing future behavior; the other idea is the emergence of preference, in which the IOWA gambling task, or perhaps the N-armed bandit problem can help in addressing.

Here's Grandmaster Nakamura crushing Svenderlunk in speed chess:

(iii) How to (automatically) capture the abstraction behind an idea?

How can this be done? But hey, what the heck can this mean?