Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!think.com!spool.mu.edu!uunet!munnari.oz.au!metro!macuni!retina!len
From: len@retina.mqcs.mq.oz.au (Len Hamey)
Newsgroups: comp.ai.neural-nets
Subject: Re: Adding 0.1 to logistic
Keywords: Logistic
Message-ID: <947@macuni.mqcc.mq.oz>
Date: 24 May 91 01:24:25 GMT
Article-I.D.: macuni.947
References: <{HV_2H$@warwick.ac.uk> <1991May23.141446.28619@fwi.uva.nl>
Sender: news@macuni.mqcc.mq.oz
Organization: Macquarie University, School of Mathematics, Physics, Computing and Electronics
Lines: 18

In article <1991May23.141446.28619@fwi.uva.nl> smagt@fwi.uva.nl (Patrick van der Smagt) writes:
>esrmm@warwick.ac.uk (Denis Anthony) writes:
>
>>I attended a seminar yesterday, at which it was stated that adding 0.1
>>to the logistic function in back prop speeds up learning by 50% (in one
>>application anyway).
>
>>If this a known phenomenum, and if so is there any reason for it ?
>
>Well, maybe this is not so hard to explain.  When initial weights are

Adding 0.1 to the logistic function is discussed in Fahlman's
paper:  An Empirical Study of Learning Speed in Back-Propagation Networks.
It is available from neuroprose.

Len Hamey			len@retina.mqcs.mq.oz.au
Lecturer in Computing
Macquarie University