🚀 go-pugleaf

In article <3829BD4D.A71EF9FA@mich.com>, mje@mich.com says...

>One interesting thing about neural nets is that they learn, without
>needing a seperate memory apart from the nuerons that generate the
>movement. If you've even seen a Tilden 'bot fired up for the first time
>you'll see it learn to walk *without* the need for an external
>validation that says "yes, you're walking, now keep doing that". The
>same elements that generate the movement learn the pattern from feedabck
>from the environment.

Well, there's external, and then there's external.  The goal that says `walking 
is good' as opposed to `sitting still is good' is external.  In real life, you 
don't discover that walking is good (and there's no reason to suppose that it 
is), until it happens to bring you into contact with more food and mates than 
your sedentary brethren.  Since the robots I've seen on TV science slots 
neither feed nor mate, one has to assume that the some goals have been 
hard-wired in by their creator.

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Ian Kemmish                   18 Durham Close, Biggleswade, Beds SG18 8HZ, UK
ian@five-d.com                Tel: +44 1767 601 361
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Behind every successful organisation stands one person who knows the secret
of how to keep the managers away from anything truly important.