Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!uunet!mcsun!hp4nl!fwi.uva.nl!smagt From: smagt@fwi.uva.nl (Patrick van der Smagt) Newsgroups: comp.ai.neural-nets Subject: Re: Hopfield net convergence Message-ID: <1991Feb22.111228.22643@fwi.uva.nl> Date: 22 Feb 91 11:12:28 GMT References: <5103@umbc3.UMBC.EDU> Sender: news@fwi.uva.nl Organization: FWI, University of Amsterdam Lines: 41 Nntp-Posting-Host: chris.fwi.uva.nl odysseas@umbc4.umbc.edu (Odysseas Pentakalos (RJE)) writes: > I am doing some research on the convergence of the > Hopfield net. Would anyone know of any papers or other sources > of information on the subject ? Any help would be very much > appreciated. You'd have to be more specific on what you mean with "convergence". Are you discussing the "learning" rule here, or rather activations update? In my opinion, "convergence" is not a very well-chosen term for Hopfield networks, it gives that bp-ish feeling which misleads since their behaviour is deterministic. Patrick van der Smagt `But wait a bit!' the oysters cried `Before we have our chat.' `For all of us are out of breath' `And some of us are fat.' `No hurry,' said the carpenter. They thanked him much for that. /\/\ \ / Organisation: Faculty of Mathematics & Computer Science / \ University of Amsterdam, Kruislaan 403, _ \/\/ _ NL-1098 SJ Amsterdam, The Netherlands | | | | Phone: +31 20 525 7524 | | /\/\ | | Fax: +31 20 525 7490 | | \ / | | | | / \ | | email: smagt@fwi.uva.nl | | \/\/ | | | \______/ | \________/ /\/\ ``The opinions expressed herein are the author's only and do \ / not necessarily reflect those of the University of Amsterdam.'' / \ \/\/ -- P.S. New address from Feb. 1: University of Amsterdam, Dept. of Computer Systems Kruislaan 403, NL--1098 SJ Amsterdam, THE NETHERLANDS fax: +31 20 525 7490, tel: +31 20 525 7524/7515 Brought to you by Super Global Mega Corp .com