Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!yale!cmcl2!rnd!ssen
From: ssen@rnd.GBA.NYU.EDU (Sahana Sen)
Newsgroups: comp.ai.neural-nets
Subject: Interpreting a Neural Net.
Message-ID: <6132@rnd.GBA.NYU.EDU>
Date: 14 Oct 90 23:23:31 GMT
Organization: NYU Stern School of Business
Lines: 10

I'm exploring using neural networks for modeling hierarchical decision 
processes - whether the network can uncover the sequence of attributes
or decision variables used on its own without building in a prespecified 
structure.  Also is it posiible to interpret the connection weights in an
unstuctured net to understand any relationship between the inputs and
outputs ?  Any pointers would be appreciated. Send mail to :
ssen@rnd.gba.nyu.edu 

Thanks a lot.
S.Sen