Path: utzoo!attcan!utgpu!jarvis.csri.toronto.edu!rutgers!apple!voder!berlioz!andrew
From: andrew@berlioz (Lord Snooty @ The Giant Poisoned Electric Head )
Newsgroups: comp.ai.neural-nets
Subject: Re: When does a hopfield net converge ?
Summary: help wanted
Message-ID: <418@berlioz.nsc.com>
Date: 12 Jul 89 19:48:49 GMT
References: <6009@uklirb.UUCP> <3738@cps3xx.UUCP> <3376@ncsuvx.ncsu.edu>
Organization: National Semiconductor, Santa Clara
Lines: 16

In article <3376@ncsuvx.ncsu.edu>, thomae@cslvs5.ncsu.edu (Doug Thomae) writes:
> [..] The basic idea behind the proof is to
> show that a Lyaponov (sp?) function exists for the network, and then
> use a theorem from control theory that says that if such a function 
> exists for a network, then the system is stable. A good text on 
> control theory should have all the gory details [..].

I see Lyapunov-type arguments being extensively used in the NN literature.
However, I have no texts dealing with methods whereby one can perform
intelligent searches for appropriate Lyapunov functions. Can anyone suggest
apprpriate texts for this purpose?
-- 
...................................................................
Andrew Palfreyman	I should have been a pair of ragged claws
nsc!berlioz!andrew	Scuttling across the floors of silent seas
...................................................................