Path: utzoo!attcan!uunet!tank!ux1.cso.uiuc.edu!iuvax!cica!tut.cis.ohio-state.edu!ucbvax!decwrl!nsc!voder!dtg.nsc.com!andrew
From: andrew@dtg.nsc.com (Lord Snooty @ The Giant Poisoned Electric Head       )
Newsgroups: comp.ai.neural-nets
Subject: Re: Using NN to program NN
Summary: and smaller fleas to bite 'em...
Message-ID: <620@berlioz.nsc.com>
Date: 8 Feb 90 00:23:30 GMT
References: <4914@itivax.iti.org>
Distribution: comp
Organization: National Semiconductor, Santa Clara
Lines: 12

In article <4914@itivax.iti.org>, ajb@itivax.iti.org (Al Boehnlein) writes:
> Has any one ever though about using a neural net to
> program a neural net.  It would seem that a neural net
> might be just the thing to use to determine what weights
> to change, and how much to change them, when adding
> a new example to a network.

I had this thought three years ago, and have done nothing about it.
Formally, of course, it's "turtles all the way down", isn't it? :-)
-- 
...........................................................................
Andrew Palfreyman	andrew@dtg.nsc.com	Albania before April!