Copy Link
Add to Bookmark
Report
Machine Learning List Vol. 4 No. 15
Machine Learning List: Vol. 4 No. 15
Saturday, July 25, 1992
Contents:
Machine Learning 9:1
Graduate Research Assistantship in Machine Learning
The Second International Workshop On Multistrategy Learning
Call for Papers, Applications of AI (XI)
1992 Cognitive Science Society Conf. - Short Program
Fifth International Conference on Genetic Algorithms
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 pub/ml-list/V<X>/<N> or N.Z where X and N are
the volume and number of the issue; ID: anonymous PASSWORD: <your mail address>
----------------------------------------------------------------------
From: Tom Dietterich <tgd@icsi.berkeley.EDU>
Date: Fri, 24 Jul 92 09:16:02 PDT
Subject: Machine Learning 9:1
MACHINE LEARNING Volume 9, Number 1, June 1992
Editorial:
Machine Learning: A Maturing Field
Jaime Carbonell
Papers:
Dynamic Parameter Encoding for Genetic Algorithms
N. N. Schraudolph and R. K. Belew
Higher-Order and Model Logic as a Framework for Explanation-Based
Generalization
S. Dietzen and F. Pfenning
The Utility of Knowledge in Inductive Learning
M. Pazzani and D. Kibler
Book Review:
Judd: Neural Network Design and the Complexity of Learning
V. Honavar
A Reply to Honavar's Book Review
J. Stephen Judd
-----
Subscriptions - Volumes 8 and 9 (8 issues)
---- $88.00 Individual, member of AAAI
---- $140.00 Individual
---- $301.00 Institutional
Kluwer Academic Publishers, P.O. Box 358, Accord Station, Hingham, MA
02018-0358 (AAAI members please include membership number).
------------------------------
Date: Thu, 23 Jul 92 16:54:10 EDT
From: Gheorghe Tecuci <tecuci@aic.gmu.EDU>
Subject: Graduate Research Assistantship in Machine Learning
GRADUATE RESEARCH ASSISTANTSHIP
IN MACHINE LEARNING
We are looking for a Graduate Research Assistant to do basic
research in Multistrategy Learning which is one of the newest and
most promising research directions in Machine Learning.
Multistrategy learning is concerned with the development of
methods and systems that integrate several learning strategies in
order to overcome the limitations of the single strategy learning
methods such as empirical inductive learning, explanation-based
learning, case-based learning, abductive learning, and others.
The research will be mainly supported by a grant from the National
Science Foundation and will be done at the Center for Artificial
Intelligence, under the supervision of Dr. George Tecuci.
The candidate should have the following qualities:
o interest in obtaining a PhD degree in Multistrategy Learning;
o a dedication to excellence;
o basic knowledge in AI and good programming skills
(LISP and/or PROLOG);
o solid background in Computer Science
reflected by high Grade Point Average.
He/she should submit the following documents:
o application letter and statement of interests;
o detailed resume (including the list of courses taken
in the MS/BS program);
o description of his/her knowledge in Artificial Intelligence
and Programming;
o a list of references (names, addresses, phones, faxes,
and/or e-mails).
to
Dr. George Tecuci
Center for Artificial Intelligence,
Department of Computer Science
School of Information Technology and Engineering
George Mason University, 4400 University Dr.,
Fairfax, VA 22030, USA
e-mail: tecuci@aic.gmu.edu
fax: (703) 993-3729
General information:
The School of Information Technology and Engineering at George Mason
University is one of the fastest growing and most dynamic educational
and research organizations covering all basic areas of information
science and engineering, including computer science and artificial
intelligence. With five academic departments, approximately 85 faculty
members, around 1000 masters students and 300 doctoral students, the
school offers a very versatile and challenging environment for
research and education at the Masters and Ph.D. level. Recognizing
the importance of Artificial Intelligence, the School has created, in
1988, an interdisciplinary Center for Artificial Intelligence that
conducts advanced research in artificial intelligence and cognitive
science. The Center has a leading and internationally recognized
research laboratory for machine learning and inference, and offers its
researchers and students an outstanding environment and
state-of-the-art computer facilities.
George Mason University is located 16 miles west of Washington D.C.,
close to the Blue Ridge Mountains, Chesapeake Bay, historic mount
Vernon and picturesque Alexandria. It is also near the Dulles Corridor
and Tyson's Corner, which are among the largest centers of high
technology in the US.
------------------------------
Date: Wed, 22 Jul 92 17:17:25 EDT
From: Multistrategy Learning Workshop 1993 <msl93@aic.gmu.EDU>
Subject: The Second International Workshop On Multistrategy Learning
******************************************************
CALL FOR PAPERS
THE SECOND INTERNATIONAL WORKSHOP ON
MULTISTRATEGY LEARNING
May 26 - 29, 1993
Hilltop Inn, Harpers Ferry, West Virginia
International Workshops on Multistrategy Learning provide a forum
for researchers to present and discuss their results on multistrategy
learning methods and systems, the interrelationships between
different learning strategies, and the relationship of machine learning
methods and paradigms to human learning. Topics of interest
include, but are not limited to, the following:
o comparative analyses of learning strategies, approaches and
paradigms
o computational models of human knowledge and skill acquisition,
and comparisons with machine learning methods
o general learning theories and frameworks for multistrategy
learning
o methods and architectures for learning systems that integrate
various combinations of inferential strategies and/or computational
paradigms, e.g., empirical and analytical learning, empirical
induction with abstraction, abduction and/or analogy, constructive
induction and plausible reasoning, quantitative and qualitative
discovery, symbolic and subsymbolic learning, etc.
o applications of multistrategy learning systems to real-world
problems.
The Workshop will be held in picturesque and historical Harpers
Ferry, located at the intersection of Virginia, West Virginia and
Maryland. Harpers Ferry is easily accessible from the Dulles
International Airport and from the Washington, D.C. railway
station. To maintain a workshop atmosphere, the attendance will be
limited to approximately 60 participants. The Workshop is
sponsored by the Office of Naval Research and organized by
George Mason University.
Workshop Chair
Ryszard S. Michalski, George Mason University
E-mail: michalski@aic.gmu.edu
Program Chair
Gheorghe Tecuci, George Mason University and
Romanian Research Institute for Informatics
E-mail: tecuci@aic.gmu.edu
Program Committee
Jaime Carbonell, Carnegie Mellon University
Yves Kodratoff, CNRS & University of Paris-South
Stan Matwin, University of Ottawa
Raymond Mooney, University of Texas at Austin
Katharina Morik, University of Dortmund
Michael Pazzani, University of California at Irvine
Luc de Raedt, Catholic University of Leuven
Ashwin Ram, Georgia Institute of Technology
Stuart Russell, University of California at Berkeley
Lorenza Saitta, University of Torino
Derek Sleeman, University of Aberdeen
Jude Shavlik, University of Wisconsin
Kurt VanLehn, University of Pittsburgh
Bradley Whitehall, United Tech. R.C., East Hartford
David Wilkins, U. of Illinois at Urbana-Champaign
Jianping Zhang, Utah State University
Local Arrangements
Michael Hieb
Nina Kaull
Janusz Wnek
George Mason University
E-mail: {hieb, nkaull, jwnek}@aic.gmu.edu
Address for correspondence
R. S. Michalski / G. Tecuci (MSL93)
Center for Artificial Intelligence
George Mason University
4400 University Dr., Fairfax, VA 22030
E-mail: msl93@aic.gmu.edu
Fax: (703) 993-3729, Tel: (703) 993-1719
Submissions:
o Four copies of the paper should arrive at the above address
by February 1, 1993.
o Notifications of acceptance or rejection will be sent by March 15.
o Final papers should arrive by April 15.
Remark:
The Proceedings of the First International Workshop on
Multistrategy Learning, held on November 7-9, 1991,
can be obtained by sending e-mail to nkaull@aic.gmu.edu
or by writing to the above address.
------------------------------
From: Usama Fayyad <fayyad@ai-cyclops.jpl.nasa.GOV>
Message-Id: <9207222242.AA07394@AIG.Jpl.Nasa.Gov>
Subject: Call for Papers, Applications of AI (XI)
APPLICATIONS OF AI (XI): Knowledge-Based Systems in Aerospace & Industry
April 12-14, 1993
Marriott's Orlando World Center
Resort and Convention Center
Orlando, Florida, U.S.A.
Sponsored by: SPIE - The Society for Optical Engineering
In cooperation with: AAAI - The American Assoc. for Artificial Intelligence
AIAA - The American Inst. of Aeronautics & Astronautics
IEEE Computer Society
IEEE Systems, Man, and Cybernetics Society
The Eleventh Applications of Artificial Intelligence Conference will be
held April 12-14 in Orlando, FL. We invite you to submit a paper by the
deadline of Sept. 14, 1992. Details of areas and deadlines given below.
Conference Co-Chairs:
Usama M. Fayyad Ramasamy Uthurusamy
Jet Propulsion Lab General Motors Research Laboratories
California Institute of Technology
Program Committee:
Ray Bareiss, Northwestern Univ. | Steven Lytinen, The Univ. of Michigan
James Bezdek, Univ. of West Florida | Stephen C.Y. Lu, Univ. of Illinois
Gautam Biswas, Vanderbilt Univ. | Ray Mooney, Univ. of Texas at Austin
Wray Buntine, NASA Ames Research Ctr.| Gregory Piatetsky-Shapiro, GTE Labs
Steve Chien, Jet Propulsion Lab | J.Ross Quinlan, Univ. of Sydney
T. Dillon, La Trobe Univ. | Ethan Scarl, Boeing Computer Services
Richard Doyle, Jet Propulsion Lab | Jude Shavlik, Univ. of Wisconsin
Doug Fisher, Vanderbilt Univ. | Prakash Shenoy, Univ. of Kansas
Paul Fishwick, Univ. of Florida | N.S. Sridharan, Intel Corporation
David Franke, MCC | Evangelos Simoudis, Lockheed Aerospace
Ashok Goel, Georgia Tech. | Stephen Smith, Carnegie Mellon Univ.
Larry Hall, Univ. of South Florida | Jon Sticklen, Michigan State Univ.
Yumi Iwasaki, Stanford Univ. | R. Zurawsky, Swinburne Inst. of Tech.
Ramesh Jain, The Univ. of Michigan |
This year we will focus on techniques and applications that deal with
actual industrial and aerospace applications of AI, machine learning,
and reasoning systems.
Topics of interest include but are not limited to:
1. Machine Learning
2. Industrial and Aerospace Applications
3. Diagnostic Systems
4. Knowledge Acquisition and Refinement
5. Knowledge Based Systems: Verification and Validation
6. Manufacturing Systems
7. Case-Based Reasoning
8. Functional Reasoning
9. Model-Based and Qualitative Reasoning
10. Multilevel and Integrated Reasoning Systems
11. Planning and Scheduling
12. Design
13. Training and Tutoring Systems
14. Intelligent Interfaces and Natural Language Processing
15. Intelligent Database Systems
16. Parallel Architectures
In addition there will be 2-3 plenary sessions, and one or more panel
discussions. We also solicit suggestions for special sessions (e.g., Case-Based
Tutoring, Reactive Planning in Space Missions). A one-page description of such
a suggestion should be sent to the Conference Chairs, who will then forward it
to appropriate members of the Program Committee for evaluation. Selection will
be based on how well the topic relates to the general theme of the conference,
and the level of interest it is likely to generate.
To submit a paper, send four copies of a complete paper not exceeding 10 pages
single-spaced (approx. 5000 words) including figures and bibliography by
September 14, 1992 to:
Applications of AI XI: KBS
SPIE, P.O. Box 10
1000 20th Street
Bellingham, WA 98225.
Tele: (206)-676-3290; Telefax: (206)-647-1445.
Submissions will be reviewed by at least two members of the program committee
and reviews will be returned to the authors. It is important that
each paper clearly state the problem which is being addressed, the contribution
that has been made, and the relation to the current state of the art.
The program committee and conference chairs will make a selection of the best
papers accepted, and these authors will be invited to submit a revised version
of their paper to one or more special issues of journals in AI (to be decided
later).
Papers submitted to the Knowledge-Based Systems conference should not also be
submitted to the Machine Vision & Robotics conference of Applications of AI XI.
Questions about which conference is most suitable for a particular paper
should be directed to the program chairmen.
Each presenter is generally allowed 20 to 25 minutes for presentation, plus a
brief discussion period (about 5 minutes). SPIE will provide the following
media equipment free of charge: 35 mm carousel slide projectors, overhead
projectors, electronic pointers and VHS format video display.
Author Benefits
Authors and coauthors who attend the conference will be accorded a
reduced-rate registration fee, a complimentary one-year non-voting
membership in SPIE (if never before a member), and other special benefits.
IMPORTANT DATES: PAPERS DUE: September 14, 1992.
ACCEPT/REJECT LETTERS SENT BY: November 20, 1992
CAMERA-READY PAPERS (5000 words) DUE: January 18, 1993.
CONFERENCE DATES: April 12-16, 1993.
Further questions may be directed to (e-mail preferred):
Dr. Usama Fayyad Dr. Ramasamy Uthurusamy
AI Group M/S 525-3660 Computer Science Department
Jet Propulsion Lab General Motors Research Labs
California Institute of Technology 30500 Mound Rd.
Pasadena, CA 91109 Warren, MI 48090-9055
phone: (818) 306-6197 phone: (313) 986-1989
fax: (818)-306-6912. fax: (313) 986-9356
e-mail: Fayyad@aig.jpl.nasa.gov e-mail: Samy@gmr.com
------------------------------
Date: Tue, 21 Jul 92 10:55:42 EST
From: "CANDACE SHERTZER, 5-4658, PSYCHOLOGY 341" <CSHERTZE@ucs.indiana.EDU>
Subject: 1992 Cognitive Science Society Conf. - Short Program
The Fourteenth Annual Conference of
The Cognitive Science Society
July 29 -- August 1, 1992
Indiana University
Short Program
(Full Program available upon request)
Wednesday July 29, 1992
2:00-7:00 p.m. REGISTRATION
5:30-7:00 WELCOMING RECEPTION
7:00-8:15 PLENARY SPEAKER:
John Holland, University of Michigan and
Santa Fe Institute
Must learning precede cognition?
Thursday July 30, 1992
9:00-10:15 a.m. PLENARY SPEAKER:
Daniel Dennett, Tufts University
Problems with some models of consciousness
10:50-12:30 SYMPOSIUM:
Computational models of evolution as tools for
cognitive science
ORGANIZER:
Richard Belew, UC, San Diego
PARTICIPANTS:
Richard Belew, UC, San Diego
Daniel Dennett, Tufts Univ.
Merlin Donald, Queens Univ.
John Holland, Univ. of Michigan and Santa Fe Inst.
ABSTRACT:
The general theme to be pursued by our panel is an analogy:
Neural Nets : Learning :: Genetic Algorithms : Evolution
That is, from the perspective of computational tools for cognitive science,
GAs can potentially play a role like that now played by NNets. Of course,
this analogy is a truism, obviously false, and just about everything else
in between, so discussion should be lively. Some of the more specific
topics that are likely to be touched upon include:
- Adapationism: GA's are typically cast as function optimizers; doesn't
that mean they embody Panglossian misconceptions as they are used
as models of cognitive systems?
- Is the recently renewed interest in evolutionary constraints on
cognition part of the recent movement (by some) away from
symbolic accounts of cognition and towards "neo-cybernetic" ones,
or are evolutionary considerations orthogonal to these issues?
- Are there really any fundamental differences between the kinds of
computation we call "evolutionary" and those we call "learning"?
That is, do these names simply reflect the original inspiration
behind two successful classes of adaptive algorithms, which can
be shown to really be interchangeable forms of machine learning?
The panel will begin with short position statements by each of the
participants, followed by discussion among them. Questions from the
audience will also be solicited.
10:50-12:30 SUBMITTED TALKS:
22 talks in the areas of planning, connectionist
models, development, psycholinguistics, and imagery
and visual reasoning
2:00-3:40 SYMPOSIUM:
Similarity and representation in early cognitive
development
ORGANIZER:
Mary Jo Rattermann, Hampshire College
PARTICIPANTS AND TALK TITLES:
Judy DeLoach and Don Marzolf
Similarity and symbols in early development;
Linda Smith and Michael Gasser
Learning words and learning to selectively attend;
Mary Jo Rattermann
Effects of relational labels on children's use of
similarity;
Dedre Gentner
Mechanisms of re-representation in learning and
development
ABSTRACT:
The role of similarity in cognitive development has often been
characterized as that of a provider of false information, leading children
to false inferences and incorrect conclusions, or as that of an inferior
fallback strategy, to be used only when other more sophisticated strategies
fail (e.g., Keil, 1989; Quine, 1969). An alternative to this bleak view of
the role of similarity is that, rather than being a hindrance, similarity
can be a powerful tool for acquiring and organizing knowledge. Indeed,
similarity comparisons can often lead to new insights into complex
concepts and the abstraction of deeper relational structures. This
symposium is organized around the view of similarity as a tool for
cognitive development. Each of the presentations provides an example
of similarity comparisons functioning as a catalyst for change and
growth in children's representational knowledge.
SYMPOSIUM:
Representation: Who needs it?
ORGANIZERS:
Timothy van Gelder, Indiana Univ. and
Beth Preston, Univ. of Georgia
PARTICIPANTS:
Beth Preston, Univ. of Georgia
Michael Turvey, Univ. of Connecticut
Dan Lloyd, Trinity College
Randy Beer, Case Western Reserve Univ.
Brian Smith, Xerox PARC
ABSTRACT:
Cognitive science is based on the idea that cognition is
information processing, typically conceived as some kind of
manipulation of representations. There are however disinters within
the discipline. Some have argued that the neural mechanisms
underlying at least some human capacities cannot be regarded as
representational. Others have argued that the cognizing systems
typically need representational capacities far more limited than
standardly assumed by most people in cognitive science. This symposium
will gather together researchers from a variety of areas who have
argued against representation in one way or another, as well as one or
two articulate defenders of representation. The aim is to address
questions such as: Does the brain make use of representations? What
kinds of functions, if any, must use representations? What conditions
must a structure or process satisfy to count as representation? Is
there cognition without representation? Can over-representing the
world be as much of a problem as under-representing it?
2:00-3:40 SUBMITTED TALKS:
24 talks in the areas of memory, scientific discovery,
discourse, learning and reactivity, and connectionist
models of language I
4:15-5:30 PLENARY SPEAKER:
Richard Shiffrin, Indiana University
Memory representation, storage and retrieval
5:30 GALA BANQUET (optional) featuring Bernhard Flury,
Indiana University
Friday July 31, 1992
9:00-10:15 a.m. PLENARY SPEAKER:
Elizabeth Bates, University of California, San Diego
Crosslinguistic studies of language breakdown in aphasia
10:50-12:30 SYMPOSIUM:
Dynamic processes in music cognition
ORGANIZERS:
Caroline Palmer, The Ohio State University
and Allen Winold, Indiana University
PARTICIPANTS AND TALK TITLES:
Marilyn Boltz, Haverford College
The generation of temporal expectancies in musical
perception
Jamshed Bharucha, Dartmouth College
Dynamic aspects of pitch and timbre
Ben Miller, Simmons College
Don Scarborough, Brooklyn College
and Jackie Jones, Brooklyn College
Duration discrimination in meter perception
Helga Winold, Indiana Univ.
Esther Thelen, Indiana Univ.
and Beverly Ulrich, Indiana Univ.
Cognitive dynamics of cello performance: Bowing
by highly skilled cellists
ABSTRACT:
As one of the richest and most complex sources of expression among
humans, musical behavior provides an excellent domain for study of the
communication of structure in a system fraught with multiple meanings or
interpretations. Because music is a temporally defined acoustic signal,
its understanding requires dynamic cognitive processes (those sensitive
to change over time). Questions such as whether dynamic processes
underlying musical communication reflect cognitive constraints on other
forms of human communication are the topic of this symposium. The talks
listed below represent the most current research across disciplines on
the dynamic processes in music cognition, with special focus on temporally
varying processes demanded by complex acoustic sources of information.
SYMPOSIUM:
Reasoning and visual representations
ORGANIZER:
K. Jon Barwise, Indiana University
PARTICIPANTS:
John Etchemendy, Stanford Univ.
Keith Stenning, Edinburgh Univ.
and Karen Myers, SRI International
ABSTRACT:
The development of powerful computational platforms for creating
diagrams and other forms of visual representations has led to renewed
interest in the cognitive properties of such representations. Why is
it that humans find them so useful? How is visually presented information
integrated with information presented in other forms? What are the logical
properties of visual representations? In this symposium a logician,
psychologist, and computer scientist survey work in this area and comment
on it from the perspective of their own work.
10:50-12:30 SUBMITTED TALKS:
25 talks in the areas of: vision, case-based
reasoning, similarity and categories, cognitive
neuroscience, and connectionist models of language II
2:00-3:40 SYMPOSIUM:
Dynamics in the control and coordination of action
ORGANIZERS:
Geoffrey Bingham, Indiana University
and Bruce Kay, Brown University,)
PARTICIPANTS AND TALK TITLES:
E. Thelen and B. Kay
Dynamic developments in the development of dynamics;
E. Saltzman
Dynamics of speech production;
R. Schmidt
The coordination of actions between two people:
Are oscillatory dynamics involved?
ABSTRACT:
Dynamics is becoming a major conceptual framework and modeling
tool in cognitive science. The use of dynamics in psychology originated
largely in studies of perception and action. The symposium will consist
of tutorial presentations of recent progress in dynamical models of human
action.
SYMPOSIUM:
Goal-driven learning
ORGANIZERS:
David Leake, Indiana University
and Ashwin Ram, Georgia Institute of Technology
PARTICIPANTS AND TALK TITLES:
Larry Barsalou, Univ. of Chicago
Goals and tasks in category formation and learning;
David Leake, Indiana University
Task-driven explanation;
Ryszard Michalski, George Mason Univ.
Learning goals in machine learning
Evelyn Ng, Simon Fraser Univ.
Goal orientation and the design of instruction;
Paul Thagard, Univ. of Waterloo
Goals in analogy and problem solving;
Ashwin Ram, Georgia Inst. of Tech.
Meta-reasoning about knowledge goals for learning
ABSTRACT:
In artificial intelligence, psychology, and education, a growing body
of research supports the view that learning is a goal-directed process.
Experimental studies show that people with different goals process information
differently; work in machine learning presents functional arguments for goal-
based focusing of learner effort. The symposium brings together researchers
from diverse research areas to discuss issues in how learning goals arise, how
they affect learner decisions of when and what to learn, and how they guide the
learning
process.
2:00-3:40 SUBMITTED TALKS:
23 talks in the areas of event perception, expertise,
choice, and problem solving, sentence comprehensions,
analogy and metaphor, and associative learning
4:15-5:30 PLENARY SPEAKER:
Douglas Hofstadter, Indiana University
The centrality of analogy-making in human cognition
7:00-8:40 POSTER SESSION I: 41 posters will be presented
Saturday August 1, 1992
9:00-10:15 a.m. PLENARY SPEAKER:
Martha Farah, Carnegie-Mellon University
Is an object an object an object?
Neuropsychological evidence for domain-specificity
in visual object recognition
10:50-12:30 SYMPOSIUM:
Speech perception and spoken language processing
ORGANIZERS:
David Pisoni, Indiana University
and Robert Peterson, Indiana University
PARTICIPANTS AND TALK TITLES:
Joanne Miller, Northeastern Univ.
Phonetic categories: Internal structure and context;
Carol Fowler, Haskins Laboratories and Dartmouth College
The nature of acoustic invarients for speech perception;
Gary Dell, University of Illinois
Phonological frames and phological speech errors
Paul Luce, SUNY at Buffalo and
Edward Auer, Jr., SUNY at Buffalo
Understanding spoken words
Robert Peterson, Indiana University
Preparation of form information in production
Peter Eimas, Brown University
The limited influence of postlexical
representations on prelixical representations
James Sawusch, SUNY at Buffalo and
Deborah Gagnon, SUNY at Buffalo
The segmental representation of spoken words
ABSTRACT:
The field of spoken language processing is a rich and very diverse
area of investigation. Topics of current interest include issues in speech
perception, spoken word recognition and lexical access as well as a host of
problems in language production. In this symposium we will bring together
a number of active researchers who will summarize the current state of research
and theory in this area. General themes in Cognitive Science will be
emphasized.
SYMPOSIUM:
Analogy, high-level perception, and categorization
ORGANIZERS:
Douglas Hofstadter, Indiana University
and Melanie Mitchell, University of Michigan and
Santa Fe Institute
PARTICIPANTS:
Melanie Mitchell, Univ. of Michigan and Santa Fe Inst.,
Dedre Gentner, Northwestern Univ.,
Robert Goldstone, Indiana Univ.,
Bipin Indurkhya, Boston Univ.,
Boicho Kokinov, New Bulgarian Univ.
ABSTRACT:
Analogy-making is a central research area in cognitive science, but there
is no broad agreement on just what analogy-making is, what its role in thought
is, and how it should best me modeled. Analogy-making has been characterized
by some as a special-purpose mode of thought used in problem-solving, driven
by a specific problem-solving purpose. Others characterize it very
differently, as a type of "abstract perception" that pervades thought at
all levels, that is most often carried out without any specific purpose,
and that is governed by the same mental mechanisms as perceptual and
categorization processes.
In this symposium the panel will discuss the following question:
To what extent should analogy-making be viewed as an unconscious perceptual
or categorization process, or to what extent should analogy-making be seen
as a more conscious reasoning activity? In other words, is it meaningful
to draw a sharp distinction between recognition of members of category and
the making of analogies? If so, where should this distinction be drawn?
And what implications does this distinction have for the construction of
models of analogy-making.
10:50-12:30 SUBMITTED TALKS:
18 talks in the areas of Feature salience and
reminding, explanation, tutoring and modeling of
students, and foundations
2:00-3:40 POSTER SESSION II: 45 posters will be presented
4:15-5:30 PLENARY SPEAKER:
Michael Turvey, University of Connecticut
Ecological foundations of cognition.
8:00 OPERA (optional) Rigoletto
------------------------------
Subject: Fifth International Conference on Genetic Algorithms
From: rob@galab2.mh.ua.edu
Fifth International Conference
on Genetic Algorithms
ICGA93
17-22 July, 1993
University of Illinois at
Urbana-Champaign
PRELIMINARY ANNOUNCEMENT
The Fifth International Conference on Genetic Algorithms (ICGA-93),
will be held July 17-22, 1993 at the University of Illinois at
Urbana-Champaign. This meeting brings together an international
community of researchers and practitioners from academia and
industry interested in algorithms suggested by the processes of
natural evolution. Topics of interest will include the design, analysis,
and application of genetic algorithms in optimization and machine learning.
Machine learning architectures of interest include classifier systems and
connectionist schemes that use genetic algorithms.
Papers discussing how genetic algorithms are related to evolving system
modeling (e.g., modeling of nervous system evolution, computational ethology,
artificial life, economics, etc.) are also encouraged.
A formal call for papers for ICGA-93 will be released in the coming weeks.
In the meanwhile, for further information contact one of the conference
co-chairs,
Dave Schaffer ((914) 945-6168, ds1@philabs.philips.com) or
Dave Goldberg ((217) 333-0897, GOLDBERG@vmd.cso.uiuc.edu) or
the publicity chair,
Rob Smith ((205) 348-1618, resmith@ua1ix.ua.edu)
------------------------------
End of ML-LIST 4.15 (Digest format)
****************************************