Path: utzoo!attcan!utgpu!jarvis.csri.toronto.edu!clyde.concordia.ca!uunet!tut.cis.ohio-state.edu!cs.utexas.edu!wuarchive!ukma!uflorida!fish.cis.ufl.edu!fishwick
From: fishwick@fish.cis.ufl.edu (Paul Fishwick)
Newsgroups: comp.ai.neural-nets
Subject: Re: back-prop NNs and `SAS' regression!
Message-ID: <21541@uflorida.cis.ufl.EDU>
Date: 19 Dec 89 18:20:27 GMT
References: <220700005@uxe.cso.uiuc.edu> <1989Dec18.210859.23621@wuche2.wustl.edu> <21539@uflorida.cis.ufl.EDU> <1989Dec19.172314.16051@wuche2.wustl.edu>
Sender: news@uflorida.cis.ufl.EDU
Reply-To: fishwick@fish.cis.ufl.edu (Paul Fishwick)
Organization: UF CIS Department
Lines: 28

In article <1989Dec19.172314.16051@wuche2.wustl.edu> joshi@wuche2.UUCP (Amol Joshi) writes:

> ...
> BP-nn is more like a black-box and extracting
>knowledge like the exponential dependencies etc is impossible from the information
>about weights alone. am i missing something?
>:amol
>

I agree with Amol that extracting information from NN models directly
is more difficult. This is a general problem when analyzing any nonlinear
system. However, some NN model properties may be proved directly by
studying the set of equations that represent the neural network. On
a slightly different note, I think that is important that we always
remember that a neural network, like a signal flow graph, is just
a convenient representation for a set of equations (unless one is
interested in studying the neurophysiology aspect -- where structure
of the network may represent biological structure). Any thoughts?

-paul fishwick

+------------------------------------------------------------------------+
| Prof. Paul A. Fishwick.... INTERNET: fishwick@bikini.cis.ufl.edu       |
| Dept. of Computer Science. UUCP: gatech!uflorida!fishwick              |
| Univ. of Florida.......... PHONE: (904)-335-8036                       |
| Bldg. CSE, Room 301....... FAX is available                            |
| Gainesville, FL 32611.....                                             |
+------------------------------------------------------------------------+