Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!usc!sdd.hp.com!spool.mu.edu!munnari.oz.au!brolga!uqcspe!batserver.cs.uq.oz.au!bakker
From: bakker@cs.uq.oz.au (Paultje Bakker)
Newsgroups: comp.ai.neural-nets
Subject: Extracting Rules from a Trained Network
Message-ID: <886@uqcspe.cs.uq.oz.au>
Date: 18 Apr 91 06:01:03 GMT
Sender: news@cs.uq.oz.au
Reply-To: bakker@cs.uq.oz.au
Organization: Computer Science Department, The University of Queensland, Brisbane, Australia
Lines: 17

I am interested in pointers to any articles, researchers, papers,
or books that have investigated the extraction of rules from a
successfully trained neural network.

Does anyone know if this is indeed possible? Can human-readable
rules be deduced from the distributed weights and connections of a
neural network?

Any help would be greatly appreciated.

Paul Bakker

--
--Paul Bakker   --   email: bakker@cs.uq.oz.au
--Depts. of Computer Science/ Psychology    ------
--University of Queensland  ----           --------
--New Holland   ---     -------------    ------------