Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!howland.reston.ans.net!gatech!concert!sas!mozart.unx.sas.com!saswss
From: saswss@hotellng.unx.sas.com (Warren Sarle)
Subject: Re: which software package can train nn with step function?
Originator: saswss@hotellng.unx.sas.com
Sender: news@unx.sas.com (Noter of Newsworthy Events)
Message-ID: <CzFCBu.HIL@unx.sas.com>
Date: Thu, 17 Nov 1994 18:21:30 GMT
References:  <3aeomt$ohm@news.doit.wisc.edu>
Nntp-Posting-Host: hotellng.unx.sas.com
Organization: SAS Institute Inc.
Lines: 18


In article <3aeomt$ohm@news.doit.wisc.edu>, davidz@neuro.ece.wisc.edu (David Zhang) writes:
|> I just have a simple question: which software package can
|> train a three-layered NN with the hardlimit (step function) activation
|> function?  ...

Lester Ingber's Adaptive Simulated Annealing (ASA) would be an obvious
choice. Try anonymous ftp from ftp.alumni.caltech.edu [131.215.139.234]
in the /pub/ingber directory.




-- 

Warren S. Sarle       SAS Institute Inc.   The opinions expressed here
saswss@unx.sas.com    SAS Campus Drive     are mine and not necessarily
(919) 677-8000        Cary, NC 27513, USA  those of SAS Institute.
