Low Complexity Robots

Larry J. Elmore ljelmore at montana.campuscw.net
Wed Nov 10 16:17:18 EST 1999


Michael Edelman <mje at mich.com> wrote in message
news:3829BD4D.A71EF9FA at mich.com...
>
> ....
> > >> In article [...], Steve <rstevew at armory.com> wrote:
> > >>> This is Mark Tilden's BEAM robotics. It's malarkey.
> > >>> Cute malarkey, but still malarkey. The thing keeps
> > >>> thrashing is all, it doesn't think any more than a
> > >>> pair of dice thinks. It just tries all the numbers
> > >>> till something happens.
>
> Not quite true. Tilden's stuff models the way real neural circuits work,
> rather than trying to come up with a priori rules that approximate the
> outcome of a nueral network.
>
> 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.
>
> Now, no one's made a "nervous net" that mimics human linguistic behavior
> in the way that a lot of well-known top down AI programs do. But I would
> argue that Tilden's 'bots teach us far more about how the brain actually
> works than any top-down GOFAI program ever did.

Where can I find more info on Tilden's work? I've been reading John
Holland's "Emergence" and Gerald Edelman's "Bright Air, Brliiant Fire" and
they seem to be talking along the same lines -- _very_ different than the
vast majority of stuff I've seen about neural nets.

Larry






More information about the Neur-sci mailing list