Newsgroups: comp.ai,comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!rochester!udel!news.mathworks.com!zombie.ncsc.mil!news.duke.edu!news-feed-1.peachnet.edu!gatech!howland.reston.ans.net!spool.mu.edu!uwm.edu!fnnews.fnal.gov!gw2.att.com!nntpa!ssbunews!not-for-mail
From: flb@odutsa.nw.att.com (blackmond)
Subject: Neural Nets (Perceptron)
Message-ID: <D6H5xu.Kvs@ssbunews.ih.att.com>
Keywords:  Help
Sender: news@ssbunews.ih.att.com (Netnews Administration)
Nntp-Posting-Host: odutsa.nw.att.com
Organization: AT&T
Distribution: usa
Date: Mon, 3 Apr 1995 19:53:54 GMT
Lines: 15
Xref: glinda.oz.cs.cmu.edu comp.ai:28754 comp.ai.neural-nets:23216

If anyone can help me out.  I have a question that I need to answer for
class this week.  The teacher is giving 10 extra points for the correct
answer.  

The question is as follows:  If the activation function of all hidden units
are linear.  Show that Multilayer perceptron is equivalent to a single
layer perceptron.


I can use all the help I can get.

Thanks in advance

Francine Lathen
708-224-2381
