Copy Link
Add to Bookmark
Report
Machine Learning List Vol. 4 No. 14
Machine Learning List: Vol. 4 No. 14
Saturday, July 18, 1992
Contents:
Paradigmatic over-fitting in speech, NLP, and IR
Grammar Induction Query
Call for Participation: PEIRCE: A Conceptual Graphs Workbench
European Conference on Machine Learning - 93
Call for Papers - ICNN'93
Call for Papers - FUZZ-IEEE'93
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>
----------------------------------------------------------------------
Date: Fri, 3 Jul 92 14:08:07 CDT
From: "David D. Lewis" <lewis@tira.uchicago.EDU>
Subject: Paradigmatic over-fitting in speech, NLP, and IR
The problem of "over-fitting" by a technical community, as discussed
in the forwarded message by Rik Belew, has been explicitly recognized
by the speech understanding community. Perhaps more relevantly it has
been recognized by that part of DARPA which is a principal funder of
speech research. The result is that DARPA sponsors periodic
evaluations of speech recognition and spoken language systems (SLS)
using held back data from known data sets, as well as funding the
development of new data sets. The cost of developing data and
conducting evaluations is substantial---in the millions of dollars---
but arguably has led to considerable advances in the field. (It
should be mentioned that there is considerable debate about the pluses
and minuses of current evaluation procedures in this field. I am not a
speech researcher myself, and so won't comment.) More recently
similar evaluations (MUC-3, MUC-4), using held back data, have been
conducted for natural language processing.
Testing on held back data is not a guarantee that overfitting by a
field will be avoided. Some argue that the current emphasis on hidden
Markov modelling in speech recognition is an example of overfitting to
a particular approach to evaluation.
The field of information retrieval has been using shared data sets for
20 years or more. At the last two ACM SIGIR conferences, concerns
have been expressed that the widespread use of a half dozen or so
relatively small standard datasets has unduly guided the development
of the statistical machine learning methods used in IR. DARPA is
currently funding the development of a new, very large test collection
for text retrieval research, and is conducting evaluations of methods
with held back data. It will be interesting to see how well the
methods that many IR researchers have converged on through research on
the standard data sets hold up in these new evaluations.
Dave
David D. Lewis | net: lewis@tira.uchicago.edu
Center for Info. and Language Studies; U Chicago| ph. 312-702-6992
1100 E. 57th St.; JRL S-116 | fax. 312-702-0775
Chicago, IL 60637; USA |
------------------------------
Date: Fri, 10 Jul 92 12:26:25 EDT
From: noordewi@cs.rutgers.EDU
Subject: Grammar Induction Query
The area of grammar induction/inference (generating or inducing a
grammar from legal -- and perhaps illegal -- sentences) has received
significant attention over the years. However, much of the work has
either performed theoretical analyses of the problem or been concerned
primarily with grammar induction in the context of natural language
(as opposed to other areas in which grammar induction may occur). The
purpose of this message is to identify the "state of the art" of
practical algorithms for grammar induction.
First, we would like to identify those researchers who are actively
concentrating on applications areas for grammar induction, including
those focusing on problems arising outside natural language. We hope
to compile a list of such people to facilitate communication and
interaction among active researchers. In describing your work, it
would be helpful to include a characterization of the size and
complexity of the problem you are addressing.
Second, we are compiling a bibliography of references on the use of
"practical" grammar induction techniques, and wish to request
assistance on this endeavor.
Anyone with interests in this area may contact us at the email
addresses below. In addition, we would be grateful for literature
references, relevant workshops and pointers to public-domain
grammar-induction software. We will make the resulting bibliography
and researcher list available.
Thanks,
Mick Noordewier (noordewi@cs.rutgers.edu) Rutgers University
Haym Hirsh (hirsh@cs.rutgers.edu) Rutgers University
Lee Giles (giles@research.nj.nec.com) NEC Research Institute
Simon Lucas (sml@essex.ac.uk) University of Essex
------------------------------
Date: Thu, 16 Jul 1992 11:11:01 -0700
From: Bob Levinson <levinson@cse.ucsc.EDU>
Subject: Call for Participation: PEIRCE: A Conceptual Graphs Workbench
The PEIRCE worldwide AI project (over 50 participants in 10 countries)
intends to support innovative state-of-the-art structure learning
methods for conceptual clustering, constructive induction,
reinforcement learning, machine discovery, and automated knowledge
acquisition.
To join or for more information send e-mail to Robert Levinson
(levinson@cis.ucsc.edu) or Gerard Ellis (ged@cs.uq.oz.au)
PEIRCE: A CONCEPTUAL GRAPHS WORKBENCH
An Open, Nonproprietary, International, Collaborative Effort
The aim of this project is to fulfill the need for state-of-the-art
tools in the conceptual graphs community. Many people are working on
particular aspects of conceptual graphs theory; there are several very
good implementations of subsets of the theory; but there is not as yet
a robust, widely available set of tools for developing applications
based on conceptual graphs.
OBJECTIVES
o Produce a robust set of tools for use by a majority of the conceptual
graphs community
o Accessible to a wider community
o Markedly improve application development time
o Incorporate the best research
PLATFORM
o Core implementation language is C++
o Option of running programs in Prolog or other languages on top
of the core
o Development environment is X-Windows on UNIX workstations
o Plans for portability to Macintosh and IBM PC compatibles
MODULES
o Linear notation input and output
o Graphical editor and display
o Programming interfaces to C, C++, Prolog, and other languages
o Natural language parsers and generators
o Database storage and retrieval
o Inference/theorem-proving mechanisms
o Conceptual catalogs (ontologies)
o Learning mechanisms
o Programming in conceptual graphs with constraints
o Vision Systems
o Information Systems Engineering
o Planning
o Computer Aided Instruction
o Case Based Reasoning
The best implementation of each module will be included in PEIRCE. A
number of modules are already available, and current modules may be
replaced or upgraded as new ones are developed.
EXISTING IMPLEMENTATIONS
o Large conceptual graphs systems written in Prolog and Lisp
o CG-based expert system shells in Prolog and C++
o Parsers and generators for several natural languages
o X-Windows conceptual graphs interfaces in Prolog and C++
o Parsers for the linear form in Prolog and C++
o Graph access methods written in C and C++
o Collections of examples in the linear form
The first official Int'l Workshop on PEIRCE: A Conceptual Graphs
Workbench was held under the auspices of the Conceptual Graphs Workshop
in Las Cruces, New Mexico, in July 1992. Implementers gave demos of
their current systems, subgroups working on each of the PEIRCE modules
presented status reports, and groundrules for future participation were
established.
The first public release of the PEIRCE Workbench is scheduled for
demonstration at the International Conference on Conceptual Structures
in Quebec City, Canada, in August 1993. The first release will include
linear and graphical interfaces, a CG database, and the CGC language
with production rules designed to facilitate the integration of the
other modules. As well as some demonstration applications. Future
versions will build on this core. A tutorial on the scope and methods
of PEIRCE will also be offered.
The PEIRCE proceedings will shortly be available by anonymous ftp in
the files peirce.dvi (ps, etc):
cs.uah.edu (146.229.2.2). /pub/cg/peirce
Caretaker: Harry Delugach (delugach@cs.uah.edu)
PEIRCE PROJECT COORDINATORS
Gerard Ellis University of Queensland, Australia
Robert Levinson University of California at Santa Cruz
------------------------------
Date: Sat, 18 Jul 92 19:13:16 +0200
From: Walter Van De Velde <walter@arti17.vub.ac.be>
Subject: European Conference on Machine Learning - 93
ECML-93
************
European Conference on Machine Learning
***************************************************
5-7 April 1993
Wien, Austria
Announcement and Call for Papers
******************************************
General Information:
************************
ECML-93 will continue with the tradition of earlier EWSL's
(European Working Session on Learning) and provide a platform
for presenting the latest results in the area of machine
learning. Although ECML-93 is the first conference under this
name, it can be considered as the sixth meeting of this kind in
Europe.
Programme:
**************
The scientific programme will include an invited talk by Ross
Quinlan from the University of Sydney and presentation of
selected papers. The programme will be complemented by the
possibility of organizing discussion groups and workshops on
selected topics (8 April).
Submission of Papers:
Submissions are invited on original research covering all
aspects of machine learning including, but not limited to:
learning system architectures multi-strategy learning
inductive & deductive methods inductive logic programming
abduction automated discovery
representational change in learning learning in problem solving
reinforcement learning learning by analogy
case-based learning unsupervised learning
neural network learning genetic approaches
theory of learnability evaluation of learning methods
applications of ML
Long papers should be limited to 18 pages. Short papers
describing the work in progress should be limited to 10 pages.
Submissions should be made in four copies to the Programme
Chairman.
Important Dates:
*******************
Submission deadline: 16 October 1992
Notification of acceptance / rejection: 4 December 1992
Camera ready copy: 15 January 1993
Proposals for Discussion Groups and Workshops (8 April):
******************************************************************
Particularly welcome are proposals for discussion groups and
workshops that promote collaboration between the machine
learning and other related research areas, such as logic
programming, program transformation, probabilistic approaches,
knowledge acquisition, human learning, distributed AI etc. The
position of each group can be summarized in the form of paper
that can appear in the ECML-93 Proceedings. The submission
deadline for proposals is 1 September 1992.
Programme Chairman:
***********************
Pavel Brazdil Tel.: (+351) 2 600 1672 Ext. 106
LIACC, Rua Campo Alegre 823 Fax: (+351) 2 600 3654
4100 Porto, Portugal email: pbrazdil @ ncc.up.pt
Programme Committee:
************************
F. Bergadano (Italy) I. Bratko (Slovenia)
P. Brazdil (Portugal) L. de Raedt (Belgium)
J. G. Ganascia (France) A. Giordana (Italy)
K. de Jong (USA) A. Kakas (Cyprus)
Y. Kodratoff (France) N. Lavrac (Slovenia)
R.L. de Mantaras (Spain) K. Morik (Germany)
I. Mozetic (Austria) S. Muggleton (UK)
D. Sleeman (UK) J. Shavlik (USA)
M. van Someren (Netherl.) R. Wirth (Germany)
Local Arrangements:
************************
Igor Mozetic and Gerhard Widmer Tel.: (+43) 1 533 6112
Austrian Institute for AI, Fax: (+43) 1 532 0652
Schottengasse 3
A - 1010 Wien, Austria Email: ecml @ ai.univie.ac.at
------------------------------
Date: Fri 26 Jun 92 12:34:05-PDT
From: Enrique Ruspini <RUSPINI@ai.sri.COM>
Subject: Call for Papers - ICNN'93
1993 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS
San Francisco, California, March 28 - April 1, 1993
The IEEE Neural Networks Council is pleased to announce its 1993
International Conference on Neural Networks (ICNN'93) to be held in
San Francisco, California from March 28 to April 1, 1993. ICNN'93
will be held concurrently with the Second IEEE International
Conference on Fuzzy Systems (FUZZ-IEEE'93). Participants will be able
to attend the technical events of both meetings.
ICNN '93 will be devoted to the discussion of basic advances and
applications of neurobiological systems, neural networks, and neural
computers. Topics of interest include:
* Neurodynamics
* Associative Memories
* Intelligent Neural Networks
* Invertebrate Neural Networks
* Neural Fuzzy Systems
* Evolutionary Programming
* Optical Neurocomputers
* Supervised Learning
* Unsupervised Learning
* Sensation and Perception
* Genetic Algorithms
* Virtual Reality & Neural Networks
* Applications to:
- Image Processing and Understanding
- Optimization
- Control
- Robotics and Automation
- Signal Processing
ORGANIZATION:
General Chair: Enrique H. Ruspini
Program Chairs: Hamid R. Berenji, Elie Sanchez, Shiro Usui
PROGRAM COMMITTEE:
K. Aihara I. Aleksander L.B. Almeida G. Andeen
C. Anderson J. A. Anderson A. Andreou P. Antsaklis
J. Barhen B. Bavarian H. R. Berenji A. Bergman
J. C. Bezdek H. Bourlard D. E. Brown J. Cabestany
D. Casasent S. Colombano R. de Figueiredo M. Dufosse
R. C. Eberhart R. M. Farber J. Farrell J. Feldman
W. Fisher W. Fontana A.A. Frolov T. Fukuda
C. Glover K. Goser D. Hammerstrom M. H. Hassoun
J. Herault J. Hertz D. Hislop A. Iwata
M. Jordan C. Jorgensen L. P. Kaelbling P. Khedkar
S. Kitamura B. Kosko J. Koza C. Lau
C. Lucas R. J. Marks J. Mendel W.T. Miller
M. Mitchell S. Miyake A.F. Murray J.-P. Nadal
T. Nagano K. S. Narendra R. Newcomb E. Oja
N. Packard A. Pellionisz P. Peretto L. Personnaz
A. Prieto D. Psaltis H. Rauch T. Ray
M. B. Reid E. Sanchez J. Shavlik B. Sheu
S. Shinomoto J. Shynk P. K. Simpson N. Sonehara
D. F. Specht A. Stubberud N. Sugie H. Takagi
S. Usui D. White H. White R. Williams
E. Yodogawa S. Yoshizawa S. W. Zucker
CALL FOR PAPERS
The program committee cordially invites interested authors to submit
papers dealing with any aspects of research and applications related
to the use of neural models. Papers must be written in English and
must be received by SEPTEMBER 21, 1992. Six copies of the paper must
be submitted and the paper should not exceed 8 pages including
figures, tables, and references. Papers should be prepared on 8.5" x
11" white paper with 1" margins on all sides, using a typewriter or
letter quality printer in one column format, in Times or similar
style, 10 points or larger, and printed on one side of the paper only.
Please include title, authors name(s) and affiliation(s) on top of
first page followed by an abstract. FAX submissions are not
acceptable. Please send submissions prior to the deadline to:
Dr. Hamid Berenji, AI Research Branch, MS 269-2, NASA Ames Research Center,
Moffett Field, California 94035
CALL FOR VIDEOS:
The IEEE Neural Networks Council is pleased to announce its first
Video Proceedings program, intended to present new and significant
experimental work in the fields of artificial neural networks and
fuzzy systems, so as to enhance and complement results presented in
the Conference Proceedings. Interested researchers should submit a 2
to 3 minute video segment (preferred formats: 3/4" Betacam, or Super
VHS) and a one page information sheet (including title, author,
affiliation, address, a 200-word abstract, 2 to 3 references, and a
short acknowledgment, if needed), prior to September 21, 1992, to
Meeting Management, 5665 Oberlin Drive, Suite 110, San Diego, CA
92121. We encourage those interested in participating in this program
to write to this address for important suggestions to help in the
preparation of their submission.
TUTORIALS:
The Computational Brain: Biological Neural Networks
Terrence J. Sejnowski
The Salk Institute
Evolutionary Programming
David Fogel
Orincon Corporation
Expert Systems and Neural Networks
George Lendaris
Portland State University
Genetic Algorithms and Neural Networks
Darrell Whitley
Colorado State University
Introduction to Biological and Artificial Neural Networks
Steven Rogers
Air Force Institute of Technology
Suggestions from Cognitive Science for Neural Network Applications
James A. Anderson
Department of Cognitive and Linguistic Sciences
Brown University
FOR ADDITIONAL INFORMATION, CONTACT
Meeting Management
5665 Oberlin Drive
Suite 110
San Diego, CA 92121
Tel. (619) 453-6222
FAX (619) 535-3880
------------------------------
Date: Fri 26 Jun 92 12:35:24-PDT
From: Enrique Ruspini <RUSPINI@ai.sri.COM>
Subject: Call for Papers - FUZZ-IEEE'93
CALL FOR PAPERS
SECOND IEEE INTERNATIONAL
CONFERENCE ON FUZZY SYSTEMS
FUZZ-IEEE'93
San Francisco, California
March 28 - April 1, 1993
In recent years, increasing attention has been devoted to fuzzy-logic
approaches and to their application to the solution of real-world
problems. The Second IEEE International Conference on Fuzzy Systems (FUZZ-IEEE
'93) will be dedicated to the discussion of advances in:
* Basic Principles and Foundations of Fuzzy Logic
* Relations between Fuzzy Logic and other Approximate
Reasoning Methods
* Qualitative and Approximate-Reasoning Modeling
* Hardware Implementations of Fuzzy-Logic Algorithms
* Learning and Acquisition of Approximate Models
* Relations between Fuzzy Logic and Neural Networks
* Applications to
* System Control
* Intelligent Information Systems
* Case-Based Reasoning
* Decision Analysis
* Signal Processing
* Image Understanding
* Pattern Recognition
* Robotics and Automation
* Intelligent Vehicle and Highway Systems
CALL FOR PAPERS
In addition to the papers related to any of the above areas, the
program committee cordially invites interested authors to submit
papers dealing with any aspects of research and applications related
to the use of fuzzy models. Papers will be carefully reviewed and only
accepted papers will appear in the FUZZ-IEEE '93 Proceedings.
DEADLINE FOR PAPERS: September 21, 1992
Papers must be received by September 21, 1992. Six copies of the paper
must be submitted. The paper must be written in English and its
length should not exceed 8 pages including figures, tables, and
references. Papers must be submitted on 8-1/2" x 11" white paper with
1" margins on all four sides. They should be prepared by typewriter
or letter-quality printer in one column format, single-spaced, in
Times or similar type style, 10 points or larger, and printed on one
side of the paper only. Please include title, author(s) name(s) and
affiliation(s) on top of first page followed by an abstract. FAX
submissions are not acceptable. Please send submissions prior to the
deadline to:
Dr. Piero P. Bonissone
General Electric Corporate Research and Development
Building K-1, Room 5C32A
1 River Road
Schenectady, New York 12301
FOR ADDITIONAL INFORMATION REGARDING FUZZ-IEEE'93 PLEASE
CONTACT:
Meeting Management
5665 Oberlin Drive Suite 110
San Diego CA 92121
Tel. (619) 453-6222
FAX (619) 535-3880
------------------------------
End of ML-LIST 4.14 (Digest format)
****************************************