Parallelizing attention and credit-assignment

From: Phil Goetz (philgoetz@yahoo.com)
Date: Fri Sep 09 2005 - 11:36:10 MDT


> other hand, for purposes of attention allocation and assignment of
> credit,
> it's more effective to have centralized information-integration and
> modeling (though parallelization is possible there is a moderately
> high cost involved).

Why? Particularly assignment of credit.

> IMO assigment of credit is a good example of an AI problem that no
> one has figured out how to parallelize effectively yet.
> Traditional AI
> approaches to assignment of credit such as Q-learning, Holland's
> classifiers, or Baum's Hayek are elegantly parallel in nature, yet
> highly ineffective.

Can you give some reason why you say this?
This is important.

- Phil

__________________________________________________
Do You Yahoo!?
Tired of spam? Yahoo! Mail has the best spam protection around
http://mail.yahoo.com



This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:52 MDT