From: Chris Capel (pdf23ds@gmail.com)
Date: Tue Sep 13 2005 - 12:38:59 MDT
On 9/13/05, Michael Wilson <mwdestinystar@yahoo.co.uk> wrote:
> I find it highly
> amusing that while connectionists are aweing themselves with the opacity
> and inscrutability of their own networks, as if that was an /advantage/,
> other researchers are demonstrating how NNs operate as function
> approximators and how compact symbolic rule sets can be mined from
> trained NNs (admittadly at some information loss, but connectionists
> don't expect reliability anyway), or rule sets turned into NNs. More
> sophisticated reccurent, spiking, dynamic-toplogy or otherwise
> unconventional connectionist systems pose more of a challenge, but in
> general connectionist networks are far less opaque to appropriate
> data-mining algorithms than they appear to unaided human perception.
> While still not useful for (well-designed) AGI, this field does at least
> offer tools that may one day be useful for understanding human wetware,
> as well as puncturing some of the connectionist mystique.
Indeed, it's already been used, or so I've read in Kurzweil's new
book, to reverse-engineer human aural processing to a degree that we
can actually process stereo audio and extract positioning information
from it the same way the brain does. (He's a bit sketchy on the
details, but it's clear that there's been at least some real results
in this project. I don't have the book on hand or I'd give some
references.) And as the resolution of our view of human neurons
continues to increase, this will only get easier and easier.
Chris Capel
-- "What is it like to be a bat? What is it like to bat a bee? What is it like to be a bee being batted? What is it like to be a batted bee?" -- The Mind's I (Hofstadter, Dennet)
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:52 MDT