Path: utzoo!utgpu!jarvis.csri.toronto.edu!clyde.concordia.ca!uunet!aplcen!haven!uvaarpa!hudson!aam9n
From: aam9n@hudson.acc.virginia.edu (minai ali ahmad)
Newsgroups: comp.ai.neural-nets
Subject: Re: Using NN to program NN
Message-ID: <2601@hudson.acc.virginia.edu>
Date: 10 Feb 90 08:39:56 GMT
References: <4914@itivax.iti.org> <620@berlioz.nsc.com>
Reply-To: aam9n@hudson.acc.Virginia.EDU (minai ali ahmad)
Distribution: comp
Organization: University of Virginia, Charlottesville
Lines: 24

In article <620@berlioz.nsc.com> andrew@dtg.nsc.com (Lord Snooty @ The Giant Poisoned Electric Head       ) writes:
>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? :-)
>-- 

About 2 years ago, Lapedes and Farber reported using a neural net to program an
                                                 2   2
asymmetric Hopfield net. They basically used an N X N  symmetric net to
              2
optimize the N  connections of an N neuron net. Of course, the connections
had no symmetry limitations, which was sort of neat then, but I thought it
was a huge case of overkill. The paper appeared in Physica 22D.

>...........................................................................
>Andrew Palfreyman	andrew@dtg.nsc.com	Albania before April!
 
Ali Minai