Re: Hawkins ideas on building AI's

From: Glen M. Sizemore (gmsizemore2_at_yahoo.com)
Date: 10/24/04 

Date: Sun, 24 Oct 2004 08:30:56 -0400

B: That is pattern recognition, & that's what cortex does on every level.
> Memory/association is just another term for it.

> GS: Not exactly. Although it is true that much of what is called "memory"
is
> simply the effects of exposure to repeated presentations of stimuli
> (habituation), "pairings" of stimuli (classical conditioning), and "3-term
> contingencies" (operant conditioning), there is a bit more. That is, when
> animals are exposed to, for example, delayed match-to-sample procedures,
> they learn to do subtle things that mediate the temporal gap. The
> acquisition of such behavior is, to be sure, the result of conditioning,
but
> it is not just one simple operant response class.

B: There're probably many redundant mechanisms in the brain, evolution is
dumb but we can do better.

GS: Not that it matters much, but I don't see what this has to do with my
statement. My point, fleshed out a bit, is that "pattern recognition" is
invoked when there is some sort of antecedent stimulus control, as in
classical and operant conditioning, or some diminution of responding, as in
habituation. Especially when we are in a position to observe the generic
nature of the stimulus class, *we* talk about "pattern recognition."
Certainly the observation of such behavioral phenomena invoke, as well, the
term "memory," but so do observations of more complicated kinds of behavior,
such as that that comes to be called "short-term memory." A similar argument
applies to other sorts of "memory" phenomena. These behavioral phenomena are
more complex and probably involve multiple, subtle response classes.

> B: There're lots of redundant terms in AI, philosophy, neuroscience...,
but
> "Entities must not be multiplied unnecessarily" (Occam)

> GS: But, unfortunately, cognitive psychology's raison d'etre is the
> promiscuous invention of explanatory fictions. And cognitive psychology
has
> corrupted AI, neuroscience, etc.

B: I don't know who's corrupted whom, it seems human brain just isn't good
at abstractions.

GS: Huh? The behavior from which people infer the "possession" of an
"abstraction" arises only via culture and verbal behavior.

"bkaz" <bkaz_@hotmail.com> wrote in message
news:def186b4.0410221556.4130ce55@posting.google.com...
> > B: That is pattern recognition, & that's what cortex

Relevant Pages

  • Re: Memory modulates color appearance
    ... remembering, but that's OK: I assure that I do not decide to remember ... Rejecting the concept of "memory" prevents one to use it as a scaffold ... and architectures in brain! ... where others can observe it. ...
    (comp.ai.philosophy)
  • Re: Are static array pointers thread safe?
    ... array. ... a separate area of memory dedicated to them. ... observe all sorts of strange things in the absence of synchronization, ...
    (microsoft.public.vc.mfc)
  • Re: Thread question
    ... Since a conforming program can only have one thread, ... meaning all of them are supposed ... When you had a single CPU, no caches, and main memory, it was quite ... since there was only one place to observe it. ...
    (comp.os.linux.development.apps)
  • Re: Are static array pointers thread safe?
    ... be doing some research on memory barriers. ... array. ... observe all sorts of strange things in the absence of synchronization, ...
    (microsoft.public.vc.mfc)