Re: Hawkins ideas on building AI's

From: bkaz (bkaz__at_hotmail.com)
Date: 10/27/04 

Date: 26 Oct 2004 21:02:59 -0700

> You're right about the "variables of patterns", and this is also how
> the 30 low-level to mid-level vision areas also work. The basic
> operations in each of these areas is probably specified genetically,
> but in a rather diffuse manner, and then they are fine-tuned via
> experience, during early development. Without some structuring, it's
> hard to imagine the 30 areas could simply self-organize to in every
> individual to perform the same functions in each case, simply via
> experience. The probability of this seems very low. And even if you
> built a computer system with a very fast memory, you would still have
> to specify the basic operations to occur in the different levels.
> Again, I doubt you would ever get the correct operations simply out of
> self-organization.

I'm not sure, but I don't think it's relevant for AI. The problem is
not the memory speed per se, it's the difference between memory
formation & memory retrieval speeds, - if there's no significant
difference it should be faster & more economical to form variables for
each pattern than to store them permanently in specialized areas &
share them among patterns.
 
> Regards the generalization stuff, since you read Hawkin's book
> already, he has several multi-level sensory-motor-chain diagrams in
> later chapters ... doesn't his model indicate an increasing level of
> abstraction/generalization as you go up the chain on the one side, and
> back down it on the other? And that processing at the lower levels is
> more specific in both cases?

There's a contradiction, you can't build a hierarchy around generality
*&* novelty at the same time: novel patterns by definition lack proven
generality: previously accumulated match.

> > Here's where I differ with Hawkins (or with evolution?), my hierarchy
> > is not necessarily of composition, or of novelty, it is of generality:
> > accumulated/projected match of constituent patterns.

> > You may be right, bio-vision probably does those indiscriminate
> > transforms, sort of like image compression, but that's only because
> > it's too slow (per 'processor') to do individual pattern recognition,
> > which would be far more logical and 'cost-efficient'.
 
> Yeah, you can make a case that speed is the problem, but just the
> same, all current CV systems use a multi-level hierarchy of
> operations. Later ones in the chain build upon the output of the
> previous ones.

Needless to say, none of those CV systems scale effectively enough to
do anything interesting.

> Just because you get a bigger faster computer doesn't
> necessarily mean you can get rid of this operational hierarchy. What
> would a single-level flat-architecture algorithm be? Template
> matching? Store every single possible case? Doubtful.

You seem to be describing the exact opposite of my approach :).
My hierarchy has indefinite number of levels, but the difference among
them is strictly relativistic. They all use the same
comparison-projection algorithm per variable of an input pattern, but
those patterns have sequentially expanding syntax: spectrum of
expected variables generated by lower-level comparisons.

I will post an intro to my approach on a separate thread, but forgive
me if it's not very specific, - I feel I'm close enough to
implementation to keep the core stuff proprietary :).

Boris.

Relevant Pages

  • Re: Hawkins ideas on building AIs
    ... > built a computer system with a very fast memory, ... formation & memory retrieval speeds, ... share them among patterns. ... you can't build a hierarchy around generality ...
    (sci.cognitive)
  • Re: face-selective region
    ... comes from having utterly huge amounts of such memory. ... the cortex and other areas of brain. ... the motor hierarchy, analogous to convergence of signals going up the ... and reinforcement learning is long term memory. ...
    (comp.ai.philosophy)
  • Re: Invariant Recognition, Grandmother Cell, and Memory Hierarchy
    ... >to organize memory into feedback-driven hierarchies. ... feedback really has nothing to do with the hierarchy. ... unit in the chain of information abstraction. ...
    (comp.ai.philosophy)
  • Re: Origins of our minds?
    ... my laptop has 44 operating system processes running along with it. ... These processes are "organized patterns of information" embedded within ... a physical substrate -- the computer's solid state memory. ... computer's memory versus in the brain. ...
    (talk.origins)
  • Invariant Recognition, Grandmother Cell, and Memory Hierarchy
    ... Hawkins further writes about the importance of prediction and the need ... to organize memory into feedback-driven hierarchies. ... First, memory is organized into a huge number of individual sequences, ... In this scheme, there is no strict, unyielding hierarchy wired into ...
    (comp.ai.philosophy)