From: Phil Goetz (firstname.lastname@example.org)
Date: Fri Sep 09 2005 - 15:30:55 MDT
--- Ben Goertzel <email@example.com> wrote:
> > > IMO assigment of credit is a good example of an AI problem that
> > > 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,
> > > highly ineffective.
> > Can you give some reason why you say this?
> > This is important.
> That these methods are highly ineffective is well-known. None of
> really works, which is why none has been used as the foundation of
> reasonably functional narrow AI system let alone AGI system.
Ben - It isn't well-known to me. Can you tell me a reference to
read so I can understand why you're saying this? My impression
is that the average engineer would say that
reinforcement learning or temporal-differernce learning are
the best means of credit assignment, and the average AI researcher
would say the bucket brigade or a truth-maintenance and belief-
revision system are the best means, all of which are parallel
That systems implementing the bucket brigade aren't intelligent
doesn't mean that the bucket brigade doesn't work.
Do You Yahoo!?
Tired of spam? Yahoo! Mail has the best spam protection around
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:52 MDT