Copy Link
Add to Bookmark
Report
AIList Digest Volume 5 Issue 084
AIList Digest Monday, 23 Mar 1987 Volume 5 : Issue 84
Today's Topics:
Queries - LOOPS Newgroup & Benchmarks for Production Systems &
Expert Systems on AT&T PC6300,
Comments - Toshiba Voice Recognition Chip,
AI Tools - Genetic Algorithms,
Book - Expert Systems: The User Interface,
Paper - Categories and Counterfactuals,
Funding - White Papers on Basic Research in AI
----------------------------------------------------------------------
Date: 19 Mar 87 15:13:08 GMT
From: uwai!beverly@rsch.wisc.edu (Beverly Seavey)
Subject: LOOPS newgroups
Does anyone know how to subscribe to the LOOPS newgroup at Berkeley?
------------------------------
Date: 19 Mar 87 10:22:18 GMT
From: mcvax!ukc!icdoc!cdsm@seismo.css.gov (Chris Moss)
Subject: Benchmarks for production systems
Could anyone send me or point me to an up-to-date listing of any
benchmark figures for production systems. In particular the monkey
and bananas problem in the OPS5 book is often quoted but I don't
have any figures.
Thanks, Chris Moss.
------------------------------
Date: 20 Mar 87 16:31:35 GMT
From: ihnp4!homxb!houxm!mtuxo!mtgzy!mas@ucbvax.Berkeley.EDU
Subject: Expert Systems on AT&T PC6300
We are currently writing the requirements for an "expert"
system to do wiring designs using AT&T PC6300's. We are
exploring various languages and shells that may work best in
our domain. One of our requirements for the language/shell
is a good interface to C routines and graphic libraries.
Is there any body out there who can give us their experience
with the available expert system tools, specifically in
terms of space, speed, and customizing capabilities.
Thanks in advance.
Masood Shariff & John Kee
AT&T Middletown, NJ 07748
ihnp4!mtgzy!mas
------------------------------
Date: Wed, 18 Mar 87 02:12:33 EST
From: Alex.Waibel@CAD.CS.CMU.EDU
Subject: Toshiba Voice Recognition Chip
With respect to the inquiry about the Toshiba Voice Recognition Chip,
here's two words of caution:
First off, recognition performance claims in percent are nice to know,
but in general should be taken with a grain of salt. These
numbers are HEAVILY dependent on whether speech was recorded in a quiet or
noisy environment, whether the speaker is cooperative or not, whether the
test was done speaker-dependently or independently, whether the vocabulary
in question is ambiguous (BOOK, COOK, TOOK) or not (BOOK, UNIVERSITY).
Most of the current systems are also isolated word systems, i.e., one must
make pauses between words. Whether such a system will work or not therefore
relly depends on your particular recognition task and environment.
Japanese has also two convenient properties:
Words are mostly consonant-vowel sequences, and the Japanese writing
system (Kana) consists of essentially sequences of syllable symbols. Toshiba
and other Japanese manufacturers therefore have systems that allow the speaker
to speak one of the (in the order of 100 or so (including some alternates)
kanas at a time and have the word processor then convert a sequence of kanas
into a kanji (the chinese word symbol). Now, unfortunately, this doesn't
carry over easily into English. Since English syllables employ complex
consonants clusters, there are more in the order of 20,000 English syllables
(with 100,000 possible), which makes for a substantially harder recognition
task. Also speaking these syllables in isolation is a lot less natural than
in Japanese since our writing system isn't syllable based. The corresponding
recognition of phonemes in stead of syllables in English is a VERY hard
problem with good recognition accuracy hard to come by.
Toshiba and other manufacturers (in Japan and the USA) have also whole word
based systems, but most of them require training of the system, i.e,
all words in the vocabulary must be read in at least once by the user.
I've seen the systems at Toshiba and they do indeed do impressive work,
but as far as hooking it up to your home computer and talking away in
English, I'm afraid the story is still a little more complicated than that.
Alex Waibel, CMU
------------------------------
Date: 17 Mar 87 21:15:40 GMT
From: hpda!hpcllla!hpclisp!coulter@ucbvax.Berkeley.EDU (Michael
Coulter)
Subject: Re: Genetic Algorithms
John Holland is (or was) at U. of Mich. and has written a very nice book
on genetic algorithms. I once took a class on the subject which he taught.
If you need more information (title, publisher, isbn number, etc.), send
me a note and I'll see if I can find my copy of the book.
-- Michael Coulter ...hpda!hpcllld!coulter
------------------------------
Date: 21 Mar 87 18:05:00 GMT
From: uiucdcsm!matheus@a.cs.uiuc.edu
Subject: Re: Genetic Algorithms
Proceedings of an International Conference
on Genetic Algorithms and their Applications.
John Grefenstette, editor
July 24-26, 1985, Carnegie-Mellon University
Sponsored by:
Texas Instruments, Inc.
U.S. Navy Center for Applied Research
in Artificial Intelligence (NCARAI)
------
Some additional references:
John Holland, "Escaping Brittleness: The Possibilities of General-Purpose
Learning Algorithms Applied to Parallel Rule-Based Systems."
In, Machine Learning, Vol II, Michalski, Carbonell, Mitchell, (Eds.), 1986.
------
Larry Rendell, "Conceptual Knowledge Acquisition in Search."
In, Computational Models of Learning, L. Bolc (Ed.), Springer-Verlag, 1987.
------
David Goldberg, "Computer-aided Gas Pipeline Operation using Genetic
Algorithms and Rule Learning." Ph.D. dissertation, University of
Michigan, 1983.
Christopher J. Matheus
Inductive Learning Group
University of Illinois.
------------------------------
Date: 20 Mar 87 20:55:00 GMT
From: convex!bernhart@a.cs.uiuc.edu
Subject: Re: Genetic Algorithms
I'm delighted to find someone interested in genetic algorithms. I'm glad
I decided to wander through some notes files.
About 10 years ago I did some work in this area using adaptive hashing
as my application. My faculty advisor turned me on to the subject.
Another student did some work with pattern generation and published a
paper on the subject. His name is Gary Rogers, and last I knew he
was teaching at the Swiss Federal Institute. I'll try to find a copy
of the paper - I just moved so am a little(?!) disorganized.
Two books that will be of interest to you are:
Holland, John H. Adaptation in Natural and Artificial Systems:
An Introductory Analysis with Applications to Biology, Control,
and Artificial Intelligence. Ann Arbor: The University of
Michigan Press, 1975.
Holland is a professor of computer science at the University
of Michigan. His book references a number of dissertations.
Holland, John H., Holyoak, Keith J., Nisbett, Richard E., and
Thagard, Paul R. Induction: Processes of Inference, Learning, and
Discovery. Cambridge, MA: The MIT Press, 1986.
I just got this book a month or two ago and haven't had a
chance to look at it what with moving and all. However, after
just glancing through it, I see there is material on genetic
algorithms and classifier systems. I just happened to order
it because I saw an ad in an MIT Press circular and figured a
John Holland book would interest me. The other authors are
U of M faculty also, two in psychology and one in philosophy.
I'm interested in pursuing my research in this area again. Last Fall
I starting doing a computerized literature search through my company's
Information Center. I didn't come up with anything, but I probably didn't
just hit the right databases at first. I couldn't continue the search
because funding for those activies was cut.
Your note is the first reference I've seen to any conference on genetic
algorithms. I'd love to get my hands on those proceedings, too! Who
sponsored the conference? Where was it held? If I learn anything more,
I'll respond here. If you find out any more, I'll look out for a follow-
up response from you. I'd like to hear of any progress you make in your
research.
My most recent activities have been in the Ada arena, and I'm planning to
convert my genetic modeling work of the past into Ada. I think it's
going to work out very well.
Good luck with your pursuits!
Marcia Bernhardt
Convex Computer Corporation
701 N. Plano Rd.
Richardson, TX 75081
convex!bernhart
------------------------------
Date: Wed, 18 Mar 87 15:37:31 EST
From: Jim Hendler <hendler@brillig.umd.edu>
Subject: Book - Expert Systems: The User Interface
In response to several messages I've received at late asking questions
about a forthcoming book, here's some info:
The book, Expert systems: the user interface, will be published by
Ablex and is not due out until this summer (we hope to hit the conferences
but cannot guarantee it). Queries can be addressed to me or, preferably,
to Ablex publishers. Below is the table of contents. If you are desperate
for a copy of some chapter, please send your requests directly to the first
author. There are no pre-release copies of the entire book available.
-Jim Hendler
(hendler@brillig.umd.edu)
Expert Systems: The User Interface
J. Hendler (Editor)
Ablex Publishing Corp.
Contents
Preface -- Ben Shneiderman
Hendler, J.A. and Lewis, C.
Designing Interfaces for Expert Systems
Musen, M.A., Fagan, L.A., and Shortliffe, E.H.
Graphical Specification of Procedural Knowledge for an Expert System
Tuhrim, S., Reggia, J.A. and Floor, M.
Expert System Development: Letting the domain specialist directly
author knowledge bases.
Mittal, S., Bobrow, D.J. and DeKleer, J.
DARN: Towards a Community Memory for Diagnosis and Repair Tasks
Nau, D.S. and Gray, M.
Hierarchical Knowledge Clustering: A way to represent and Use
Problem-Solving Knowledge
Baroff, J., Simon, R., Gilman, F and Shneiderman, B.
Direct Manipulation User Interfaces for Expert Systems
Fickas, S.
Development Tools For Rule Based Systems
Hayes, P.J.
Using a Knowledge Base to Drive an Expert System Interface
with a Natural Language Component
Faneuf, R. and Zirk, S.
A UIMS for Building Metaphoric User Interfaces
Chandrasekaran, B, Tanner, M.C., and Josephson, J.R.
Explanation: The role of control strategies and deep models
Jacob, R.J.K. and Froscher, J.N.
Facilitating Change in Rule-based Systems
Stelzner, M. and Williams, M.D.
The Evolution of Interface Requirements for Expert Systems
Lehner, P.E. and Kraij, M.M.
Cognitive Impacts Of The User Interface
------------------------------
Date: Tue, 17 Mar 87 00:16:40 est
From: french@farg.umich.edu (Bob French)
Subject: categories and counterfactuals
The Role of Categories in the Generation of Counterfactuals:
A Connectionist Interpretation
by Robert M. French and Mark Weaver
Department of Electrical Engineering and Computer Science
University of Michigan
Ann Arbor, Michigan 48109
Tel. (313) 763-5875
Keywords: counterfactuals, norm theory, connectionism, categories
Abstract
This paper proposes that a fairly standard connectionist category model
can provide a mechanism for the generation of counterfactuals --
non-veridical versions of perceived events or objects. A distinction is
made between evolved counterfactuals, which generate mental spaces (as
proposed by Fauconnier), and fleeting counterfactuals, which do not. This
paper explores only the latter in detail. A connection is made with the
recently proposed counterfactual theory of Kahneman and Miller;
specifically our model shares with theirs a fundamental rule of
counterfactual production based on normality. The relationship between
counterfactuals and the psychological constructs of ``schema with
correction'' and ``goodness'' is examined. A computer simulation in support
of our model is included.
The paper has been submitted to the Cognitive Science Society Conference 1987
to be held in Seattle, WA. in July.
Anyone interested in a copy of the paper, should get in touch with
Bob French as follows: french@farg.umich.edu
------------------------------
Date: Thu, 19 Mar 87 8:21:42 EST
From: "Dr. Ron Green" (ARO | mort) <green@BRL.ARPA>
Subject: White Papers on Basic Research in AI
The Army Research Office would be interested in receiving
short white papers on proposed "Basic Research" in AI.
The pepers should discuss a planned three year research
effort with technical content discussing merits of research
topic. Mail the white papers to the following address:
US Army Research Office
P.O. Box 12211
Electronics Division(Attn: Dr. C. Ronald Green)
Research Triangle Park, NC 27709-2211
Topics of interest are purely AI as well as related topics
as applied to Computer Science.
I would prefer the "white papers" as opposed to a deluge of
telephone calls. E-mail responses will also be acceptable.
green@brl.arpa
Thanks
Ron Green
------------------------------
End of AIList Digest
********************
