Copy Link
Add to Bookmark
Report
Machine Learning List Vol. 2 No. 05
Machine Learning List: Vol. 2 No. 5
Tuesday, March 13, 1990
Contents:
NETtalk
Eric Wefald
Request for Non-artificial databases with domain theories
AI: Dead or Alive
Hawaii Conference on Biotechnology Computing
The Machine Learning List is moderated. Contributions should be relevant to
the scientific study of machine learning. Mail contributions to ml@ics.uci.edu.
Mail requests to be added or deleted to ml-request@ics.uci.edu. Back issues
may be FTP'd from ics.uci.edu in /usr2/spool/ftp/pub/ml-list/V<X>/<N> or N.Z
where X and N are the volume and number of the issue; ID & password: anonymous
------------------------------
Date: Fri, 16 Feb 90 09:09:21 -0600
From: "Carl M. Kadie" <kadie@herodotus.cs.uiuc.edu>
Subject: Pointer to Discussion of NETtalk
It you are interested in the meaning and significance of
NETtalk (an artifical neural net that learns to pronounce
English text), you may wish to look at back issues of the
Nerual Net Digest.
Specifically, vol-06-no-08 contains a discusssion by Tom Dietterich
and others that details of the NETtalk methodology and results.
vol-06-no-10 contains a reply by NETtalks author, Charles Rosenberg.
Back issues are available via anonymous ftp from hplpm.hpl.hp.com
(15.255.176.205) in the directory pub/Neuron-Digest.
- Carl Kadie
------------------------------
From: Pankaj Mehra <mehra%aquinas@uxc.cso.uiuc.edu>
Subject: Eric Wefald is no more
Date: Thu, 1 Mar 90 00:14:56 CST
I met Eric Wefald on my way to Ithaca in June 1989, and again at
IJCAI-89. He (and his advisor Dr. Stuart Russell) had just finished
designing a decision-theoretic framework for designing resource-bounded
intelligent agents. I was particularly impressed by the formal flavor of
his work.
His friends will always remember Eric as someone who had the insight and
dedication to produce ideas that make a difference.
Pankaj Mehra
University of Illinois
------------------------------
Subject: Request for Non-artificial databases with domain theories
Date: Tue, 06 Mar 90 00:48:13 -0800
From: "David W. Aha" <aha@ICS.UCI.EDU>
I continue to get requests for databases with sizeable domain theories.
Unfortunately, we have little to provide in return (other than small
domain theories used as simple examples to help exemplify how EBL systems
work). I've approached several people on this, but to no avail.
If you have publicly-distributable databases with even moderately
interesting domain theories, I would _greatly_ appreciate it if you
could forward a copy to me at aha@ics.uci.edu. I'll then include
it in our collection.
Proposed, appropriate bribes could surely be arranged and satisified.
Thanks,
David W. Aha
Co-ordinator: UCI repository for machine learning databases
(ics.uci.edu with userid and password "anonymous", under
the pub/machine-learning-databases directory)
------------------------------
Subject: Update for 'AI: Dead or Alive'
From: dietrich@bingvaxu.cc.binghamton.edu (Eric Dietrich)
Organization: SUNY Binghamton, NY
Date: 20 Feb 90 14:33:53 +0000
[This is reproduced from news.announce.conferences- MP]
*** Call for papers and discussion ***
--------------------------------
ARTIFICIAL INTELLIGENCE: AN EMERGING SCIENCE OR A DYING ART FORM?
--------------------------------
June 21-23, 1990
A workshop funded by the
Research Foundation of the State University of New York and the
American Association for Artificial Intelligence
What kind of pursuit is artificial intelligence? Is AI the study of
intelligence without regard to its realization, or a branch of psychology
which adds computer modeling to the psychologist's experimental
repertoire, or something else entirely?
There are pragmatic reasons for answering this question. AI
researchers could better utilize time and funds if their research were
based on a deeper understanding of the nature of their endeavor. If, for
example, AI is an engineering discipline, then research strategies based
on the view that AI is a science might waste considerable time and money.
Beyond pragmatic concerns are the nagging doubts that AI, at least as
it is standardly conceived, is merely a way to keep our hands busy while
the neuroscientists and neural net modelers come up to speed. This is
the view that AI is not only NOT a science, but isn't even a very good
engineering discipline, and will one day be abandoned. Since this is a
view that is gaining adherents, it is important to either refute it or
establish its plausibility, and move on.
The workshop will address these questions. Four major papers will be
given; the abstracts are below. Those interested are invited to submit
four copies of an abstract (2 to 7 pages) by May 1, 1990. To help keep
the workshop focused, authors are encouraged to use one of the four
abstracts as a springboard for discussion, or to address a question of
similar scope and content. Examples of such questions are:
1. Is AI a branch of theoretical biology? Should AI abandon its
traditional home in computer science, and seek instead to unify
models of intelligence that apply to all species and even to
species considered as a unit?
2. Is it possible to formulate testable hypotheses about intelligence
which are not solely predictions about human cognitive behavior,
and then test these hypotheses experimentally? If not, then how
important is scientific AI to the study of the human brain and
the study of human psychology?
If authors prefer structure their paper as a commentary, they can request
an extended abstract
The workshop will be kept small -- about 40 participants. The
contribution of each author will be considered for inclusion as a chapter
in a subsequent edited book, or for a paper in the Journal of
Experimental and Theoretical Artificial Intelligence.
Location: SUNY -- Binghamton, Binghamton, New York; June 21-23, 1990
Workshop Chair: Eric Dietrich
Department of Philosophy
SUNY -- Binghamton
Binghamton, New York 13901 (607) 777-2305
e-mail: dietrich@bingvaxu.cc.binghamton.edu
Accomodations: Can be arranged by calling
Holiday Inn SUNY Patti Koval
Vestal Parkway East OR Conference Coordinator
Binghamton, NY 13901 Residential Life
(607) 729-6371 SUNY -- Binghamton
(607) 777-6200
For further information, contact the workshop chair.
-------------------------------
Accompanying four abstracts:
#1
ARTIFICIAL INTELLIGENCE AND COMPUTATION THEORY
Clark Glymour
Carnegie Mellon University
Abstract
Disciplines exist partly to guarantee their members that certain things
don't have to be thought about. Artificial intelligence has become
sufficiently disciplined that many of its practitioners behave as though
they can ignore large branches of theory.
Sometimes they can. One going enterprise in machine learning is much
like literary interpretation: Some problem area in science or elsewhere
is identified, and one shows that from a reconstruction of the evidence
and the problems of the domain some fairly simple machine algorithm can
solve discovery problems. Nothing is proved or claimed (usually) about
the optimality or limitations of the algorithm. The proceedings of the
Machine Learning conferences are filled with papers of this kind. The
work of Simon's associates provides many examples, and so does much of
the work on learning to plan. One can think of these efforts as sort of
"toy" expert systems work. I have nothing against it; some of this work
is clever, some dull. Some of it is incredibly trivial.
On the other hand, there is a great deal of work in artificial
intelligence that is not just interpretive and that intends to reveal
better ways to do things of importance. In this paper, I argue that
work in non-monotonic inference, explanation-based learning,
simulation studies of the superiority of one or another inference
procedure, as well as an abundance of work in "cogntiive science" that
aims to describe human "computational architecture" all suffer from
failures to take account of the frameworks and results of aspects of
computation theory, especially of learning theory.
#2
Down with Solipsism!
The Challenge to AI from connectionism
J. Hendler
Dept. of Computer Science
Univ. of Maryland
College Park, Md. 20742
hendler@cs.umd.edu
Now, as never before in its short existence as a field, AI is facing a
challenge from the ``cognitivists'' in our ranks. For too long, too
much of the emphasis in AI research has focused on producing systems
which manipulate arbitrary symbol systems to produce other arbitrary
symbols. The growing interest in connectionist models and neural
networks, however, has been focusing on the perceptual level of
cognition. The analogy sometimes used is that AI has been looking at
the parts of the cognitive iceberg that are above water. The bulk of
the iceberg of cognition, however, still underwater, is perception,
emotion, etc. Can any field of ``intelligence'' become a science
while ignoring the bulk of the issue?
In this paper I will try to demonstrate some of the rudiments of
cognition which I believe are growing out of the connectionist
paradigm. Those of us in traditional AI must pay attention to these
results, as well as to cognitive phenomena, which derive from the fact
that intelligent entities are situated in an environment, as opposed
to solipsistic islands unto themselves. This paper is not, however, a
philosphical treatise on symbol grounding. Rather, we report on both
experimental and theoretical research being conducted which is aimed
at exploring the differences in representation learned by
connectionist systems, at understanding how well-documented cognitive
phenomena (such as priming) can be replicated in these models, and at
some types of reasoning (particularly in the area of perceptual
similiarity) which must be accounted for in a model of intelligence.
#3
What is Cognitive Science?
Bill Rapaport
Dept of Computer Science
SUNY Buffalo
Buffalo, NY 14260
rapaport@cs.buffalo.edu
My paper (as I currently conceive it), which will be based on an
encyclopedia article on cognitive science that I am writing, will survey
the nature of cognitive science as a single discipline with a particular
"outlook". Although the encyclopedia article tends to the objective and
netural, my paper for the workshop will take a firm stand on several
issues. I will (1) suggest a distinction between "multidisciplinary" and
"interdisciplinary" research (with examples from one of my own cognitive
science research projects), (2) argue that cognitive science can (or, at
least, should) be considered as a single cohesive discipline that applies
diverse methodologies to a common problem (viz., what is mind/mentality)--
as opposed to most/many other disciplines, which apply a single
methodology to diverse problems, and (3) consider to what extent the
computational view of cognitive science, whether in its weak form (the
computational "metaphor") or its strong form (cognition _is_
computation), leads to a position like that Searle calls "strong AI".
Topics that will briefly be dealt with will include: the Chinese Room
Argument, the intentional stance, and how syntax can yield semantics.
Reference:
Rapaport, William J. (1988), ``Syntactic Semantics: Foundations
of Computational Natural-Language Understanding,'' in J. H. Fetzer (ed.)
Aspects of Artificial Intelligence (Dordrecht, Holland: Kluwer Academic
Publishers): 81-131.
#4
CRYSTALLIZING THEORIES OUT OF KNOWLEDGE SOUP
John F. Sowa
IBM Systems Research
Thornwood, NY 10594
In very large knowledge bases, global consistency is practically
impossible to achieve, yet local consistency is essential for deduction
and problem solving. To preserve local consistency in an environment of
global inconsistency, this paper proposes a two-level structure: an
enormous reservoir of loosely organized encyclopedic knowledge, called
"knowledge soup"; and floating in the soup, much smaller, tightly
organized theories that resemble the typical microworlds of AI. The two
kinds of knowledge require two distinct kinds of reasoning: "abduction"
uses associative search, measures of relevance, and belief revision for
finding appropriate chunks of knowledge in the soup and assembling them
into consistent theories; and "deduction" uses classical theorem-proving
techniques for reasoning within a theory. The resulting two-level
system can attain the goals of nonmonotonic logic, while retaining the
simplicity of classical logic; it can use statistics for dealing with
uncertainty, while preserving the precision of logic in dealing with
hard-edged facts; and it can relate logics with discrete symbols to
models of continuous systems.
------------------------------
Date: Fri, 9 Mar 90 15:22:25 EST
From: Larry Hunter <hunter@work.nlm.nih.GOV>
Subject: Announcement of Hawaii Conference on Biotechnology Computing
Call for Papers and Referees
Hawaii International Conference on System Sciences - 24
Kailua-Kona, Hawaii - January 8-11, 1991
Biotechnology Computing Minitrack
The Emerging Applications and Technologies Track of HICSS-24 will
contain a special session focusing on design of computer systems for
use in biological science and engineering. The presentations will
provide a forum for the discussion of new approaches to the challenges
posed by this rapidly growing application domain.
Both the rate of innovation in biotechnology and the effective
transfer of basic scientific insights into significant application depend
crucially on a diverse and complex collection of computer systems. In
a dramatic shift over the last five years or so, nearly every
biologist working in genetics, protein structure, or other molecular
fields now routinely uses very large databases and sophisticated
analytical tools. For example, the discovery that certain oncogenes
(cancer causing genes) are point mutations of normal growth factors
depended crucially on the use of macromolecular databases and rapid
sequence searching algorithms.
The challenges of biocomputing touch on nearly all aspects of computer
science. Papers are invited that describe improvements in the power,
quality, effectiveness or ease of use of software and systems in any
bioscience or biotechnology related area. Areas of special interest
include advances in:
* Modelling of molecular dynamics, reactions, metabolic pathways or
larger biological systems
* Data structures, database designs and search engines for managing
biological information
* Molecular graphics, visualization tools and user interfaces
* Macromolecular structure and function prediction systems
* Computer-aided molecular design (including recombinant DNA)
* Automation of experimental techniques, data acquisition and other
laboratory activities
* Integrated systems, networks, standards, compatibility and
international cooperation
Instructions for authors :
Manuscripts should be 22-26 typewritten, double-spaced pages in 10 or
12 point type; do not send submissions significantly longer or
shorter. Papers must not have been previously presented or published,
nor currently submitted for journal publication. Each manuscript will
be refereed by at least five reviewers. Manuscripts should include a
title page that identifies the title of the paper, the full name(s) of
the author(s), affiliation(s), complete mailing and electronic
address(es), telephone number(s) and a 300 word abstract of the paper.
Members of the community willing to serve as referees should send
their name, electronic and physical address, phone number, and areas
of interest to the program chair. Authors of submissions to this
minitrack may not serve as referees.
Deadlines:
* A 300 word abstract is due by April 15, 1990
* Feedback to the author concerning the abstract by April 30, 1990
* Six copies of the manuscript are due by June 6, 1990
* Notification of accepted papers by September 1, 1990
* Accepted manuscripts, camera ready, are due by October 3, 1990
Send submissions and questions to:
Lawrence Hunter
National Library of Medicine
Building 38A, Mail Stop 54
Bethesda, MD 20894
(301) 496-9300
(301) 496-0673 (fax)
Hunter@nlm.nih.gov
------------------------------
END of ML-LIST 2.5
