Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!howland.reston.ans.net!Germany.EU.net!zib-berlin.de!zrz.TU-Berlin.DE!math.fu-berlin.de!gc
From: gc@pip.fpms.ac.be (Gustavo Calderon)
Subject: Theoretical Justifications
Message-ID: <M6WWBYOS@math.fu-berlin.de>
Sender: news@math.fu-berlin.de (Math Department)
Nntp-Posting-Host: pip.fpms.ac.be
Organization: Free University of Berlin, Germany
X-Newsreader: TIN [version 1.2 PL2]
Date: Fri, 3 Feb 1995 12:21:50 GMT
Lines: 17

Hi everybody,


Here I have to questions on NN design,



	Why does a neuron need a bias input ?

	Why do we need activation functions ?


I am preparing a report on NN and I would like to know what you people think the right answers are.


Thanks.

