ckennedy@ee.brunel.ac.uk (C.M.Kennedy ) (08/22/86)
The following is a list of the useful replies received so far:
From rreilly%euroies@reading.ac.uk Thu Jul 31 13:14:07 1986
Received: from reading by Mars.ee.brunel.ac.uk; Thu, 31 Jul 86 13:14:00 GMT
Received: by Onion.Cs.Reading.AC.UK with X25 (Reading Mail System 3.11/3.22)
id AA10407; Thu, 31 Jul 86 10:10:32 bst
Received: from mcvax by eagle.Ukc.AC.UK with authorised UUCP id a022369;
30 Jul 86 11:11 BST
Received: by mcvax.uucp; Wed, 30 Jul 86 10:10:10 +0200 (MET)
Message-Id: <8607300810.AA13515@mcvax.uucp>
Date: Wed, 30 Jul 86 8:56:08 BST
From: Ronan Reilly <rreilly%euroies@reading.ac.uk>
To: ckennedy@ee.brunel.ac.uk
Sender: rreilly%euroies@reading.ac.uk
Status: R
To: mcvax!ukc!reading!brueer!ckennedy
Subject: Re: Connectionist Approaches To Expert System Learning
References: <360@brueer.ee.brunel.ac.uk>
Hi,
What you're looking for, effectively, are attempts to implement
production systems within a connectionist framework. Researchers
are making progress, slowly but surely, in that direction. The
most recent paper I've come across in thge area is:
Touretzky, D. S. & Hinton, G. E. (1985). Symbols among the neurons
details of a connectionist inference architecture. In
Proceedings IJCAI '85, Los Angeles.
I've a copy of this somewhere. So if the IJCAI proceedings don't come
to hand, I'll post it onto you.
There are two books which are due to be published this year, and they
are set to be the standard reference books for the area:
Rumelhart, D. E. & McClelland, J. L. (1986). Parallel distributed
processing: Explorations in the microstructure of cognition.
Vol. 1: Foundations. Cambridge, MA: Bradford Books.
Rumelhart, D. E. & McClelland, J. L. (1986). Parallel distributed
processing: Explorations in the microstructure of cognition.
Vol. 2: Applications. Cambridge, MA: Bradford Books.
Another good source of information on the localist school of
connectionism is the University of Rochester technical report series.
They have one report which lists all their recent connectionist
reports. The address to write to is:
Computer Science Department
The University of Rochester
Rochester, NY 14627
USA
I've implemented a version of the Rochester ISCON simulator in
Salford Lisp on our Prime 750. The simulator is a flexible system
for building and testing connectionist models. You're welcome to
a copy of it. Salford Lisp is a Maclisp variant.
Regards,
Ronan
...mcvax!euroies!rreilly
From mozer@ics.ucsd.edu Sun Aug 3 12:00:12 1986
Received: from reading by Mars.ee.brunel.ac.uk; Sun, 3 Aug 86 12:00:07 GMT
Received: by Onion.Cs.Reading.AC.UK with X25 (Reading Mail System 3.11/3.22)
id AA22897; Sun, 3 Aug 86 11:54:29 bst
Received: from mcvax by eagle.Ukc.AC.UK with authorised UUCP id a018511;
3 Aug 86 8:11 BST
Received: by mcvax.uucp; Sun, 3 Aug 86 00:19:23 +0200 (MET)
Received: from s3sun.UUCP by seismo.CSS.GOV with UUCP; Sat, 2 Aug 86 17:57:29 EDT
Received: by s3sun (4.24/5.20a)
id AA18967; Sat, 2 Aug 86 14:45:22 pdt
Received: by sdcsvax.ucsd.edu (5.31/4.42)
id AA06711; Sat, 2 Aug 86 09:30:56 PDT hops=0
Date: Sat, 2 Aug 86 09:33:46 PDT
From: Mike Mozer <mozer%ics.ucsd.edu@reading.ac.uk>
Message-Id: <8608021633.AA05908@sdics.ICS>
Received: by sdics.ICS scf2.7vax; Sat, 2 Aug 86 09:33:46 PDT
To:
Mmdf-Warning: Parse error in preceding line at Ukc.AC.UK
Subject: Re: Connectionist Approaches To Expert System Learning
References: <360@brueer.ee.brunel.ac.uk>
Sender: mozer%ics.ucsd.edu@reading.ac.uk
Status: R
I've just finished a connectionist expert system paper, which I'd be glad
to send you if you're interested (need an address, though).
Here's the abstract:
RAMBOT: A connectionist expert system that learns by example
Expert systems seem to be quite the rage in Artificial Intelligence, but
getting expert knowledge into these systems is a difficult problem. One
solution would be to endow the systems with powerful learning procedures
which could discover appropriate behaviors by observing an expert in action.
A promising source of such learning procedures
can be found in recent work on connectionist networks, that is, massively
parallel networks of simple processing elements. In this paper, I discuss a
Connectionist expert system that learns to play a simple video game by
observing a human player. The game, Robots, is played on a two-dimensional
board containing the player and a number of computer-controlled robots. The
object of the game is for the player to move around the board in a
manner that will force all of the robots to collide with one another
before any robot is able to catch the player. The connectionist system
learns to associate observed situations on the board with observed
moves. It is capable not only of replicating the performance of the
human player, but of learning generalizations that apply to novel
situations.
-----
Mike Mozer
mozer@nprdc.arpa
From tfra%ur-tut@reading.ac.uk Sat Aug 9 05:38:59 1986
Received: from reading by Mars.ee.brunel.ac.uk; Sat, 9 Aug 86 05:38:53 GMT
Received: by Onion.Cs.Reading.AC.UK with X25 (Reading Mail System 3.11/3.22)
id AA19352; Sat, 9 Aug 86 05:19:55 bst
Received: from mcvax by eagle.Ukc.AC.UK with authorised UUCP id a019414;
9 Aug 86 5:15 BST
Received: by mcvax.uucp; Sat, 9 Aug 86 03:08:34 +0200 (MET)
Received: from rochester.UUCP by seismo.CSS.GOV with UUCP; Fri, 8 Aug 86 19:31:10 EDT
Received: by ur-seneca.rochester.arpa id AA28877 (4.12w); Fri, 8 Aug 86 19:06:40 edt
Received: by ur-tut.UUCP id AA27342 (4.12wj); Fri, 8 Aug 86 18:53:57 edt
Message-Id: <8608082253.27342@ur-tut.UUCP>
Date: Fri, 8 Aug 86 18:53:57 edt
From: Tom Frauenhofer <tfra%ur-tut@reading.ac.uk>
To: ckennedy@ee.brunel.ac.uk
Subject: Re: Connectionist Approaches To Expert System Learning
Newsgroups: net.ai
In-Reply-To: <360@brueer.ee.brunel.ac.uk>
Organization: U. of Rochester Computing Center
Sender: tfra%ur-tut@reading.ac.uk
Status: R
Catriona,
I am (slightly) familiar with a thesis by Gary Cotrell of the U of R here
that dealt with a connectionist approach to language understanding. I believe
he worked closely with a psychologist to figure out how people understand
language and words, and then tried to model the behavior in a connectionist
framework. You should be able to get a copy of the thesis from the Computer
Science Department here. It's not expert systems, but it is fascinating.
- Tom Frauenhofer
...!seismo!rochester!ur-tut!tfra
From sandon@ai.wisc.edu Sat Aug 9 17:25:29 1986
Received: from reading by Mars.ee.brunel.ac.uk; Sat, 9 Aug 86 17:25:20 GMT
Received: by Onion.Cs.Reading.AC.UK with X25 (Reading Mail System 3.11/3.22)
id AA21365; Sat, 9 Aug 86 16:34:56 bst
Received: from [192.5.2.16] by 44d.Cs.Ucl.AC.UK via Satnet with SMTP
id a001229; 8 Aug 86 17:40 BST
Date: Fri, 8 Aug 86 11:38:43 CDT
From: Pete Sandon <sandon%ai.wisc.edu@reading.ac.uk>
Message-Id: <8608081638.AA29509@ai.wisc.edu>
Received: by ai.wisc.edu; Fri, 8 Aug 86 11:38:43 CDT
To: ckennedy@ee.brunel.ac.uk, sandon@ai.wisc.edu
Subject: Connectionist Learning
Status: R
Hi,
You may have already received this information, but I will pass it
along anyway. Steve Gallant, at Northeastern University, has done some
work on using a modified perceptron learning algorithm for expert
system knowledge acquisition. He has written a number of tech reports
in the last few years. His email address is: sig@northeastern.csnet.
His postal address is: Steve Gallant
College of Computer Science
Boston, MA. 02115
--Pete Sandon