From: Perry E.Metzger (perry@piermont.com)
Date: Sat Nov 01 2003 - 15:00:52 MST
"Metaqualia" <metaqualia@mynichi.com> writes:
> I was thinking of a universal pattern recognition machine, something that
> will work to recognize whatever, no matter the stimulus. it will recognize
> automatically configurations with low entropy and high organization in the
> sensory input. The same machine could learn to do audio or video analysis or
> solve problems, whatever.
In the general case, what you're talking about would violate Rice's
theorem. What you're looking for would distinguish non-trivial
properties of the R.E. languages, so it is a priori impossible.
In the less general case of producing something that would work well
enough in engineering practice for a limited set of domains, it is
likely doable -- after all, we are ourselves examples.
By the way, you seem to be using entropy imprecisely. One would expect
complicated systems to have high entropy. An object with very low
entropy, like a salt crystal, isn't very complex.
> I asked myself, in the simplest case, what would it take for a basic layer
> of neurons that are activated with light intensity, to make the next layer
> wire itself to detect edges?[...]
There is a great deal of literature out there on neural nets and using
them for vision. Have you read much of it?
-- Perry E. Metzger perry@piermont.com
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:43 MDT