Newsgroups: comp.ai.shells
Subject: The name "Expert System"
From: randy.bennett@dscmail.com (Randy Bennett)
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!howland.reston.ans.net!news.moneng.mei.com!uwm.edu!msuinfo!netnews.upenn.edu!nova.voicenet.com!dscmail!randy.bennett
Distribution: world
Message-ID: <1.849.2209.0N27E7E3@dscmail.com>
References: <360358107wnr@rshome.demon.co.uk>
Date: Mon, 28 Nov 94 15:00:00 -0640
Organization: DSC/Voicenet * Ivyland, PA * (215) 443-9434
Lines: 36

NA>A lecturer in my uni. told me that "...the name Expert System is no
NA>longer being used.  These systems are now popularly called
NA>knowledge-based systems".  Do u agree?

        Well, for waht its worth...no I don't.

NA>- What exactly are Expert Systems and knowledge-based systems?

        Expert Systems are especailly designed programs which
        incorporate the knowledge of an expert to do a particular thing.
        They are designed to mimic parts of human reasoning, so ideas
        like forward and backward chaining are important.  They can also
        use forms other than rules for encoding knowledge.
        Knowledge-based systems (IMHO) can be ordinary computer programs
        with a component added to incorporate knowledge in the form of
        rules.  Chaining isn't necessary since they seem to operate in a
        linear fashion.

NA>- What's the difference between the two, if any?

        Having said all of that, I should point out that my take on this
        is purely from a practical point of view.  I am not now, nor
        have I ever been, an AI researcher or academic.

        From that point of view, I have tended to use the two terms
        interchangably.  I found alot of resistance to the term Expert
        Systems, and alot of people thinking that their problem wasn't a
        candidate since it didn't require a world-class expert to solve
        it.  Calling the same thing a knowledge based system made those
        fears go away.

Randy
randy.bennett@dscmail.com
---
  SLMR 2.1a  Me.. a skeptic?  I trust you have proof.

