Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!fas-news.harvard.edu!newspump.wustl.edu!news.ecn.bgu.edu!psuvax1!news.pop.psu.edu!news.cac.psu.edu!howland.reston.ans.net!math.ohio-state.edu!jussieu.fr!univ-lyon1.fr!swidir.switch.ch!news.unige.ch!news.unige.ch!thimm
From: thimm@cry (Georg Thimm)
Subject: Re: Adaptive Activation Functions
In-Reply-To: blam@hyde.uwindsor.ca's message of Tue, 21 Mar 1995 18:04:41 GMT
Message-ID: <THIMM.95Mar22093639@cry>
Sender: usenet@news.unige.ch
Organization: IDIAP
References: <3kn00p$roa@taloa.unice.fr> <D5sy7t.E8y@news.uwindsor.ca>
Date: Wed, 22 Mar 1995 08:36:39 GMT
Lines: 18

Hi!

If you are interested in adaptive sigmoidal functions, you probably
want to have a look at
ftp://www.idiap.ch/pub/papers/neural/thimm.gain.ps.Z, which shows that
under certain circumstances the adaptive steepness is equivalent to a
adaptive learning rate.

Have fun,
		Georg 
--
--------------------------------------------------------------
Georg Thimm                            E-mail: thimm@idiap.ch
Institut Dalle Molle d'Intelligence    Fax:  ++41 26 22 78 18
Artificielle Perceptive (IDIAP)        Tel.: ++41 26 22 76 64
Case Postale 592		       WWW: http://www.idiap.ch
1920 Martigny / Suisse
--------------------------------------------------------------
