Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!howland.reston.ans.net!agate!hpg30a.csc.cuhk.hk!hkuxb.hku.hk!hkuxa.hku.hk!h9218252
From: h9218252@hkuxa.hku.hk (IP Yu Ting)
Subject: Why Sigmoid functions ??????
Message-ID: <D4A17L.Cy1@hkuxb.hku.hk>
Sender: usenet@hkuxb.hku.hk (USENET News System)
Nntp-Posting-Host: hkuxa.hku.hk
Organization: The University of Hong Kong
X-Newsreader: TIN [version 1.1 PL6]
Date: Mon, 20 Feb 1995 02:21:21 GMT
Lines: 18


Hi there,

The sigmoid function is a popular choice of neuron transfer functions
in feed-forward neural networks.  Is it because of its relationship
with the Boltzmann distribution equation ?

If it is, then what is so special about that relationship the relationship
that makes sigmoid good for NN works ?

What is the effect of the sigmoid constant (i.e. the temperature term) ?
For sure we know that as T->0, it becomes a step function.  I mean, then
what is the effect on the performance of NN of such a change ?

Thanks a lot.

--D. Ip

