Copy Link
Add to Bookmark
Report
Machine Learning List Vol. 4 No. 22
Machine Learning List: Vol. 4 No. 22
Wednesday, Nov 22, 1992
Contents:
Machine Learning List: Vol. 4 No. 22
FOIL
Research Assistant at Strathclyde
PostDoc at Sydney
Statistical routines for speedup learning
New Book and videotape on Genetic Programming
ECML Workshop on ML and Text Analysis
Conference on Uncertainty in Artificial Intelligence
CP for AI and Stats Workshop
Artificial Neural Networks and Expert Systems
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, 6 Nov 1992 09:37:38 +1100
From: Ross Quinlan <quinlan@ml2.cs.su.oz.au>
Subject: FOIL
New version of FOIL
Version 4 is available by anonymous ftp from cluster.cs.su.oz.au (129.78.8.1).
File ~ftp/pub/foil4.sh (583Kb) contains source, a brief manual, and several
sample datasets.
Principal changes to version 4 are:
* a new method of filtering recursive definitions (encompassing complex
tasks such as learning Ackermann's function)
* several heuristics for guiding the search for clauses and for reordering
definitions; these lead to faster searches and more intelligible results
* general increase in speed
------------------------------
Date: Fri, 13 Nov 92 11:52:13 GMT
From: ross@stams.strath.ac.UK
To: ml@ics.uci.edu
Subject: Research Assistant at Strathclyde
RESEARCH ASSISTANT (6 MONTHS)
We expect shortly to appoint a Research Assistant in the StatLog project
based at the University of Strathclyde (Scotland). This is a temporary post
with duration December 1992 to May 1993.
The remuneration would be on the British SERC RA 1A scale
(11399 to 18165 pounds per annum).
A separate sum of money would be available for travel.
The post would be suitable for recent M.Sc. or Ph.D. graduates with a strong
machine learning or statistical background.
STATLOG PROJECT
This is an Esprit project which is nearing completion.
In this phase of the project, we are comparing many types of Machine-Learning,
neural net and statistical algorithms on problems in discrimination, with an
emphasis on large-scale, complex commercial and industrial problems.
The methods to be used include some of the more fashionable methods such as
causal trees, neural nets and genetic algorithms, as well as the more
traditional methods like discriminant analysis and decision trees.
STRATHCLYDE UNIVERSITY STATISTICS DEPARTMENT (Scotland, U.K.)
Strathclyde supplies the Technical leadership in the project, with
two members of the Academic Staff involved. Two RA's will be working
full-time on the project.
At Strathclyde, we have special responsibility for classical
statistical methods, but we are also interested in more modern
ones like symbolic machine learning, neural nets, projection
pursuit and kernel density methods.
As part of our responsibilites, visits to and by the other
partners are expected. The other partners are:
Brainware (Berlin); Daimler-Benz (Ulm, Germany);
Granada University (Spain); ISoft (Gif sur Yvette, France);
Dresden University (Germany); Porto University (Portugal).
We would expect the person appointed to this post to help in
the application of several statistical or neural net procedures to a wide
variety of datasets. Ability to program in C, Fortran or Splus,
or familiarity with Sun workstations would be an advantage.
If this is of any interest to you, please e-mail us a
potted C.V., and even a reference or two if you feel keen.
Please address correspondence/telephone enquiries/fax messages to:
Dr. R.J. Henery or Dr. J.M.O. Mitchell
Department of Statistics and Modelling Science
Strathclyde University
Richmond Street
Glasgow G1 1XH
Scotland
U.K.
Tel: +44-041-552-4400 X3661
Fax: +44-041-552-4711
e-mail: r.j.henery@uk.ac.strath.vaxa
------------------------------
Date: Fri, 6 Nov 1992 09:37:38 +1100
From: Ross Quinlan <quinlan@ml2.cs.su.oz.au>
Subject: PostDoc at Sydney
To: pazzani@ics.uci.edu
Message-ID: <9211051544.aa04515@q2.ics.uci.edu>
Unversity of Sydney
Postdoctoral position 1993-1994
A second position in empirical machine learning will be available starting
in 1993 (start date is fairly flexible). The position will be attached to
a project investigating new learning algorithms (both propositional and
first-order), hybrid learning methods( e.g. combinations of instance-based
and symbolic approaches), and aspects of constructive induction.
If you are interested, contact Ross Quinlan (quinlan@cs.su.oz.au) for further
information.
------------------------------
Date: Thu, 12 Nov 92 19:18:46 -0800
From: Oren Etzioni <etzioni@cs.washington.EDU>
Subject: Statistical routines for speedup learning
I've written some handy common lisp routines for performing
statistical hypothesis tests (specifically, the SIGN and RANKED SIGN
tests). The routines are particularly well-suited for analyzing
speedup learning experiments with censored or truncated data. A paper
on the subject will appear in the Machine Learning Journal, but I
would like to make the code available in the meantime. If you are
interested send me mail at etzioni@cs.washington.edu.
Paper abstract:
Speedup learning systems are typically evaluated by comparing their
impact on a problem solver's performance. The impact is measured by
running the problem solver, before and after learning, on a sample of
problems randomly drawn from some distribution. Often, the
experimenter imposes a bound on the CPU time the problem solver is
allowed to spend on any individual problem. Segre et al. [MLJ '91]
argue that the experimenter's choice of time bound can bias the
results of the experiment. To address this problem, we present
statistical hypothesis tests specifically designed to analyze speedup
learning data and eliminate this bias. We apply the tests to the data
reported in [Etzioni '90], and show that most (but not all) the
differences observed are statistically significant.
------------------------------
Date: Sun, 15 Nov 92 16:39:50 PST
From: John Koza <koza@cs.stanford.EDU>
Subject: New Book and videotape on Genetic Programming
BOOK AND VIDEOTAPE ON GENETIC PROGRAMMING
A new book and a one-hour videotape (in VHS NTSC, PAL, and SECAM
formats) on genetic programming are now available from the MIT
Press.
NEW BOOK...
GENETIC PROGRAMMING: ON THE PROGRAMMING OF COMPUTERS BY
MEANS OF NATURAL SELECTION
by John R. Koza, Stanford University
The recently developed genetic programming paradigm provides a
way to genetically breed a computer program to solve a wide variety
of problems. Genetic programming starts with a population of
randomly created computer programs and iteratively applies the
Darwinian reproduction operation and the genetic crossover (sexual
recombination) operation in order to breed better individual
programs. The book describes and illustrates genetic programming
with 81 examples from various fields.
840 pages. 270 Illustrations. ISBN 0-262-11170-5.
Contents...
1 Introduction and Overview
2 Pervasiveness of the Problem of Program Induction
3 Introduction to Genetic Algorithms
4 The Representation Problem for Genetic Algorithms
5 Overview of Genetic Programming
6 Detailed Description of Genetic Programming
7 Four Introductory Examples of Genetic Programming
8 Amount of Processing Required to Solve a Problem
9 Nonrandomness of Genetic Programming
10 Symbolic Regression - Error-Driven Evolution
11 Control - Cost-Driven Evolution
12 Evolution of Emergent Behavior
13 Evolution of Subsumption
14 Entropy-Driven Evolution
15 Evolution of Strategy
16 Co-Evolution
17 Evolution of Classification
18 Iteration, Recursion, and Setting
19 Evolution of Constrained Syntactic Structures
20 Evolution of Building Blocks
21 Evolution of Hierarchies of Building Blocks
22 Parallelization of Genetic Programming
23 Ruggedness of Genetic Programming
24 Extraneous Variables and Functions
25 Operational Issues
26 Review of Genetic Programming
27 Comparison with Other Paradigms
28 Spontaneous Emergence of Self-Replicating and Self-Improving
Computer Programs
29 Conclusions
Appendices contain simple software in Common LISP for
implementing experiments in genetic programming.
ONE-HOUR VIDEOTAPE...
GENETIC PROGRAMMING: THE MOVIE
by John R. Koza and James P. Rice, Stanford University
The one-hour videotape (in VHS NTSC, PAL, and SECAM formats)
provides a general introduction to genetic programming and a
visualization of actual computer runs for 22 of the problems
discussed in the book GENETIC PROGRAMMING: ON THE PROGRAMMING
OF COMPUTER BY MEANS OF NATURAL SELECTION. The problems
include symbolic regression, the intertwined spirals, the artificial
ant, the truck backer upper, broom balancing, wall following, box
moving, the discrete pursuer-evader game, the differential pursuer-
evader game, inverse kinematics for controlling a robot arm,
emergent collecting behavior, emergent central place foraging, the
integer randomizer, the one-dimensional cellular automaton
randomizer, the two-dimensional cellular automaton randomizer,
task prioritization (Pac Man), programmatic image compression,
solving numeric equations for a numeric root, optimization of lizard
foraging, Boolean function learning for the 11-multiplexer, co-
evolution of game-playing strategies, and hierarchical automatic
function definition as applied to learning the Boolean even-11-
parity function.
__________________________ORDER FORM______________________
PHONE: 800-326-4471 TOLL-FREE or 617-625-8569
MAIL: The MIT Press, 55 Hayward Street, Cambridge, MA 02142
FAX: 617-625-9080
Please send
____ copies of the book GENETIC PROGRAMMING: ON THE
PROGRAMMING OF COMPUTERS BY MEANS OF NATURAL SELECTION by
John R. Koza (KOZGII) (ISBN 0-262-11170-5) @ $55.00.
____ copies of the one-hour videotape GENETIC PROGRAMMING: THE
MOVIE by John R. Koza and James P. Rice in VHS NTSC format
(KOZGVV) (ISBN 0-262-61084-1) @$34.95
____ copies of the videotape in PAL format (KOZGPV) (ISBN 0-262-
61087-6) @$44.95
____ copies of the videotape in SECAM format (KOZGSV) (ISBN 0-
262-61088-4) @44.95.
Name __________________________________
Address_________________________________
City____________________________________
State_________________Zip________________
Country_________________________________
Phone Number ___________________________
$ _______ Total
$ _______ Shipping and Handling ($3 per item. Outside U.S. and
Canada, add $6 per item for surface rate or $22 per item for airmail)
$ _______ Canada - Add 7% GST
$ _______ Total due MIT Press
__ Payment attached (check payable to The MIT Press in U.S. funds)
__ Please charge to my VISA or MASTERCARD credit card
Number ________________________________
Credit Card Expires _________________________________
Signature ________________________________
[I haven't read the book (yet), but I have seen the movie and it's
both educational and entertaining: Mike]
------------------------------
Subject: ECML Workshop on ML and Text Analysis
Date: Sat, 7 Nov 92 16:01:59 MET
From: David Powers <marpia@rhrk.uni-kl.de>
CALL FOR PAPERS
ECML'93 Workshop on ML techniques and Text Analysis
(European Conference on Machine Learning)
Vienna - 8th April 1993
Keywords: Machine Learning, Natural Language, Text Analysis
Focus of the workshop
Although the ideal of a completely transparent natural language
interface to a computer is still way out of reach, there is an
abundance of interesting applications of ML techniques to text
analysis. Note that people are producing more and more texts at
increasing speed. It is impossible to read everything. Therefore the
need for automatic text analysis is growing rapidly. One of the
reasons interesting NL applications are still out of reach is the
knowledge acquisition bottleneck in the definition of grammars and
lexicons. ML techniques are beginning to be used to alleviate this
problem. Examples of interesting projects are:
Semantic and syntactic disambiguation of texts
Text Search algorithms for free text databases
Automated document classification
Automatic creation of dictionaries
Automatic creation of indexes
Self-learning parsers
Therefore we are organizing a workshop devoted to syntactic and semantic
analysis of natural languages using machine learning techniques. The
workshop will focus on the analysis of textual information, either
supervised or unsupervised.
Motivation
The field of machine learning of language has witnessed substantial
growth in interest and results in the past few years. Machine Learning
techniques are in principle very useful in the context of language
learning. Yet language learning has special problems of its own, that
are not in the focus of interest of most researchers in the ML
community, e.g.:
- The special algebraic structure of linguistic samples
- The highly structured and complex nature of language,
and in particular the supposed irregularities, synonyms,
metaphors etc.
- The complex interplay between the partial information about
syntax and the lack of definition in the semantics of the samples.
- Special biases concerning the `cooperativeness' of the author
or speaker
These aspects call for another approach incorporating different
algorithms, different complexity measures and different sampling
techniques. At the moment contributions to this field tend to be
scattered over various conferences (ML, AI, linguistics, psychology
etc.). It is the aim of this workshop to bring researchers in this area
together.
Contributions
Particularly welcome are contributions that describe practical
solutions to existing problems. Topics of interest include but are
not limited to:
Syntactic Learning
Semantic Learning
Lexical Disambiguation
Linguistic Pattern Matching
Statistical Techniques applied to NL
Lexical Acquisition
Automatic analysis of bi-lingual corpora
Complexity measures for texts
New ML techniques geared to NL
Information theoretic results and measures
Text analysis and existing ML techniques
Connectionism
Genetic Algorithms
Explanation based Learning
Statistical inference
Inductive Logic Programming
Case-based and Memory-based Learning
Form of the workshop
1 day, Presentations, Discussion, workshop proceedings. A position
paper in the conference proceedings of ECML-93. The workshop will
be held after the ECML-93 main conference, on 8 April 1993.
Submitted papers should be 10-20 pages in length in the format for the ECML
conference. People wishing to attend the workshop but not present a paper need
only send a short research description. Submissions by electronic mail
are preferred, and should be sent to the chair and one other committee member
(either in plain ASCII or standard LaTeX article format). Hardcopy
submissions must be sent in triplicate to the chair at the address below.
Submissions must ARRIVE by 18 January 1992.
Committee:
Walter Daelemans walter@kub.nl
David Powers powers@dfki.uni-kl.de
Von-Wun Soo soo@cs.nthu.edu.tw
Larry Reeker reeker@ida.org
Pieter Adriaans (chair) pieter@syllogic.nl
Coordinator's Address:
Pieter Adriaans
Syllogic B.V.
Houten
The Netherlands
SUMMARY OF DATES:
January 18 - Papers and research dscriptions due
February 1 - Acceptance notification
February 22 - Final version of papers due
------------------------------
Date: Fri, 6 Nov 92 14:38:56 PST
From: David Heckerman <heckerma@cs.ucla.EDU>
Subject: Conference on Uncertainty in Artificial Intelligence
NINTH ANNUAL CONFERENCE ON UNCERTAINTY IN ARTIFICIAL INTELLIGENCE
July 9-11, 1993, Washington D.C.
CALL FOR PAPERS
The ninth annual Conference on Uncertainty in Artificial Intelligence will be
devoted to methods for reasoning under uncertainty as applied to problems in
artificial intelligence. The conference's scope covers the full range of
approaches to automated and interactive reasoning and decision making under
uncertainty, including both qualitative and numeric methods.
We seek papers on fundamental theoretical issues, on computational techniques
for uncertain reasoning, and on the foundations of alternative paradigms of
uncertain reasoning. Topics of interest include:
- Foundations of uncertainty concepts
- Representations of uncertain knowledge and their semantics
- Knowledge acquisition
- Construction of uncertainty models from data
- Uncertainty in machine learning
- Automated planning and decision making under uncertainty
- Algorithms for uncertain inference
- Pooling of uncertain evidence
- Belief updating and inconsistency handling in uncertain knowledge bases
- Explanation and summarization of uncertain information
- Control of reasoning and real-time architectures
This year, we hope to attract more contributions that emphasize real-world
applications of uncertain reasoning. Questions of particular interest
include:
- Why was it necessary to represent uncertainty in your domain?
- What kind of uncertainties does your application address?
- Why did you decide to use your particular uncertainty formalism?
- What theoretical problems, if any, did you encounter?
- What practical problems did you encounter?
- Did users of your system find the results or recommendations useful?
- Did the introduction of your system lead to improvements in reasoning
or decision making?
- What methods were used to validate the effectiveness of the systems?
Papers will be carefully refereed for originality, significance, technical
soundness, and clarity of exposition. Papers may be accepted for presentation
in plenary or poster sessions. Some key applications oriented work may be
presented both in a plenary session and in a poster session where more
technical details can be discussed. All accepted papers will be included in
the published proceedings. Outstanding student papers may be selected for
special distinction.
Five copies of each paper should be sent to one of the Program Co-Chairs by
February 5, 1993. The first page should include a descriptive title, the
names, addresses, and student status of all authors, a brief abstract, and
salient keywords or other topic indicators. Acceptance notices will be sent
by March 29, 1993. Final camera-ready papers, incorporating reviewers'
suggestions, will be due approximately five weeks later. There will be an
eight-page limit on proceedings papers, with a few extra pages available for
a fee.
Program Co-Chairs (paper submissions):
David Heckerman
Department of Computer Science, UCLA
Boelter Hall, Room 3531
405 Hilgard Avenue
Los Angeles, CA 90024-1596
tel: (310) 825-2695, fax: (310) 825-2273
email: heckerman@cs.ucla.edu
Abe Mamdani
Deptartment of Electronic Engineering
Queen Mary & Westfield College
Mile End Road
London E1 4NS
tel: +44-71-975-5341, fax: +44-81-981-0259
e-mail: e.h.mamdani@qmw.ac.uk
General Co-Chair (conference inquiries):
Michael P. Wellman
Department of EECS, University of Michigan
Artificial Intelligence Laboratory
Ann Arbor, MI 48109
tel: (313) 764-6894, fax: (313) 763-1260
email: wellman@engin.umich.edu
Conference Committee: Piero Bonissone, Peter Cheeseman, Mike Clarke, Bruce
D'Ambrosio, Didier Dubois, Max Henrion, John Fox, Rudolf Kruse, Henry Kyburg,
John Lemmer, Tod Levitt, Ramon Lopez de Mantaras, Serafin Moral, Ramesh Patil,
Judea Pearl, Enrique Ruspini, Ross Shachter, Glenn Shafer, Philippe Smets,
Kurt Sundermeyer, Lotfi Zadeh.
------------------------------
Date: Wed, 4 Nov 92 14:34:00 PST
From: Wray Buntine <wray@ptolemy.arc.nasa.GOV>
Subject: CP for AI and Stats Workshop
This is a shortened version of the 2nd CP that excludes the schedule.
If you'ld like to see the schedule (list of papers & posters being
presented) then email your request to
wray@kronos.arc.nasa.gov
2nd Call for Participants
for
Fourth International Workshop on
Artificial Intelligence
and
Statistics
January 3-6, 1993
Ft. Lauderdale, Florida
PURPOSE:
This is the fourth in a series of workshops which has
brought together researchers in Artificial Intelligence and in
Statistics to discuss problems of mutual interest. The result has
been an unqualified success. The exchange has broadened research
in both fields and has strongly encouraged interdisciplinary work.
This workshop will have as its primary theme:
``Selecting models from data''
FORMAT:
Approximately 60 papers by leading researchers in Artificial
Intelligence and Statistics have been selected for presentation.
To encourage interaction and a broad exchange of ideas, the
presentations will be limited to 20 discussion papers in single
session meetings over the three days. Focussed poster sessions,
each with a short presentation, provide the means for presenting
and discussing the remaining 40 research papers.
Attendance at the workshop is *not* limited.
The three days of research presentations will be preceded by a day
of tutorials. These are intended to expose researchers in each
field to the methodology used in the other field.
LANGUAGE:
The language will be English.
FORMAT:
One day of tutorials and three days of focussed poster sessions,
presentations and panels. The presentations are scheduled in the
mornings and evenings, leaving
the afternoons free for discussions in more relaxed environments.
PROGRAM COMMITTEE:
General Chair: R.W. Oldford U. of Waterloo, Canada
Programme Chair: P. Cheeseman NASA (Ames), USA
Members:
W. Buntine NASA (Ames), USA
Wm. Dumouchel BBN, USA
D.J. Hand Open University, UK
W.A. Gale AT&T Bell Labs, USA
H. Lenz Free University, Germany
D. Lubinsky AT&T Bell Labs, USA
M. Deutsch-McLeish U. of Guelph, Canada
E. Neufeld U. of Saskatchewan, Canada
J. Pearl UCLA, USA
D. Pregibon AT&T Bell Labs, USA
P. Shenoy U. of Kansas, USA
P. Smythe JPL, USA
SPONSORS:
Society for Artificial Intelligence And Statistics
International Association for Statistical Computing
REGISTRATION: All fees paid:
Before Dec 1, 1992 After Dec 1, 1992
Scientific programme: $225 $275
Full-time Students $135 $175
- Registration fee includes three continental breakfasts and two
lunches supplied at the workshop site.
- Students must supply proof of full-time student status (at the
workshop) to be eligible for reduced rates.
A REGISTRATION FORM APPEARS AT THE END OF THIS MESSAGE.
TUTORIALS: There are four three hour tutorials planned.
Two introducing statistical methodology to AI researchers
and two introducing AI methodology to statistical researchers.
Before Dec 1, 1992 After Dec 1, 1992
Per Tutorial $65 $75
Full-time Students $40 $45
The tutorials are introductions to the following topics:
1. Learning, including a discussion of neural networks.
Speaker: Doug Fisher, Vanderbilt University
Orientation: AI for statisticians
2. Graphical models, causal reasoning, and qualitative
decision making.
Speaker: Judea Pearl, UCLA
Orientation: AI for statisticians.
3. Overview of statistical models.
Emphasis on generalised linear and additive models.
Speaker: Daryl Pregibon, AT&T Bell Labs
Orientation: Statistics for AI researchers.
4. Introduction to Statistics.
General introduction to statistical topics
Speaker: Wray Buntine, NASA Ames
Orientation: Statistics for AI researchers.
Please indicate which tutorial(s) you are registering for.
PAYMENT OF FEES:
All workshop fees are payable by cheque or money order in U.S.
dollars (drawn on a U.S. bank) to the Society for Artificial
Intelligence and Statistics.
Send cheque or money order to:
R.W. Oldford
Chair, 4th Int'l Workshop on A.I. & Stats.
Dept. of Statistics & Actuarial Science
University of Waterloo
Waterloo, Ontario
N2L 3G1
CANADA
NOTE: ACCOMODATIONS MUST BE ARRANGED DIRECTLY WITH THE HOTEL.
ACCOMODATION: We have arranged for a block of rooms to be available to
participants at the Workshop site hotel for $85 per night
(single or double + tax). Arrangements must be made
directly with the hotel. Please mention the Workshop on
all communications. Rates are available Jan 1 to Jan 10
(if booked before Dec 17, 1992).
Pier 66 Resort and Marina
2301 S.E. 17th Street Causeway
Ft. Lauderdale, Florida 33316
(305) 525 6666
(800) 327 3796 (USA only)
(800) 432 1956 (Florida only)
Fax: (305) 728 3551
Telex: 441-650
REGISTRATION FORM:
4th International Workshop on
AI and Statistics
January 3-6, 1993
Ft. Lauderdale, Florida
Name: _______________________________
Affiliation: _______________________________
Address: _____________________________________________
_____________________________________________
_____________________________________________
_____________________________________________
e-mail: _____________________________________________
Fax: ___________________________
Phone: ___________________________
Scientific Programme Registration ...................... US$___________
Tutorial 1. Learning ................................... US$___________
Tutorial 2. Causal Reasoning ........................... US$___________
Tutorial 3. Statistical Models ......................... US$___________
Tutorial 4. Introduction to Statistics ................. US$___________
Total Payment .......................................... US$___________
------------------------------
From: NKASABOV@gandalf.otago.ac.nz
Date: 3 Nov 92 09:07:59 GMT+1200
Subject: Artificial Neural Networks and Expert Systems
FIRST CALL FOR PAPERS AND PARTICIPANTS
The First New Zealand International Two-stream Conference
on Artificial Neural Networks and Expert Systems- ANNES'93
November 24-26, 1993
University of Otago, Dunedin, New Zealand
LETTER from the President of the New Zealand Computer Society:
Dear Colleague,
It has been suggested by NZCS members and members of the Expert
Systems Interest Group that we should hold a conference on Expert
Systems in 1993. We are now glad to invite you to participate to The
First New Zealand International Two-stream Conference on Artificial
Neural Networks and Expert Systems ANNES'93. The aim of the conference
is to gather together scientists, industry and business
representatives in order to enrich their knowledge and technological
skills in developing knowledge based systems and their numerous
applications. I would recommend this conference to you and urge you to
attend.
Yours faithfully,
Philip Sallis
TOPICS OF INTEREST
* Artificial neural networks: models; architectures; algorithms; software
tools; hardware implementations; cognitive models of the brain and their
impact.
* Neural networks for problem solving: handling large experimental data
bases; speech-, image- and text processing; time-series prognosis;
control; diagnosis, etc.
* Fuzzy systems: methods; tools; software and hardware implementations;
fuzzy systems for problem solving.
* Expert systems: methods for representing inexact data and uncertain
knowledge; approximate reasoning; tools and systems; object-oriented
systems.
* Hybrid systems: integrating neural networks and AI-techniques;
integrating neural networks and fuzzy systems; extending existing
software tools with fuzzy reasoning and neural nets.
* Industrial applications of expert systems and neural networks:
manufacturing; process control; quality testing; etc.
* Business applications of neural networks and expert systems: Finance;
Economics; Marketing; Management; Banking; etc.
* Applications of neural networks and expert systems in Agriculture,
Environment protection, Medicine, Geographic information systems; and
other application areas.
* The impact of neural networks and expert systems to the future IT
development.
INVITED KEYNOTE SPEAKERS
Professor Takeshi Yamakawa, Department of Computer Science and
Control, Kyushu Institute of Technology, Chairman of the Fuzzy Logic
Systems Institute (Japan).
Professor V.Rao Vemuri, Department of Applied Science, University of
California, Davis (U.S.A.).
CALL FOR PAPERS
Papers must be received by April 30, 1993. They will be reviewed by
senior researchers in the field and the authors will be informed about
the decisions at the end of the review process by June 30, 1993. Final
versions of the accepted papers should be submitted by 30 July 1993. A
recommended size for a paper would be between 4 and 10 pages. All
accepted papers will be published in the conference proceedings, which
will be available at the conference for distribution to all the regular
conference registrants. As the conference is a multi-disciplinary
meeting the papers are required to be comprehensible to a wider rather
than to a very specialised audience. Papers will be presented at the
conference either in an oral or in a poster session. Please submit three
(3) copies (one camera-ready original and two copies) of the paper
written in English on A4-format white paper with one inch margins on all
four sides, in one-column format, single-spaced, in Times or similar font
of 12 points, and printed on one side of the page only. Centred at the top
of the first page should be the complete title, author(s), mailing and e-
mailing addresses, following by an abstract, followed by the text.
TUTORIALS
During the first day of the conference the following 3-hour tutorials
will be organized:
1. The basics of artificial neural networks.
2. The basics of fuzzy systems. Fuzzy systems
applications.
3. Neural networks for problem solving.
4. Expert systems- tools and systems.
These aim at providing basic knowledge in the subject area. The tutorial
fee is not included in the conference fee. Tutorial materials will be
distributed among the participants.
EXHIBITION
Companies and university research laboratories are encouraged to
exhibit their developed or distributed software and hardware products.
There will be an additional fee of NZ$50 for exhibiting products at the
conference.
STUDENTS SESSION
A postgraduate session will be organised. Postgraduate students are
encouraged to submit papers to this session following the same formal
requirements for paper submission. The submitted papers will be
published in a separate brochure.
VIDEO TRACK
A video session will be organised which will allow participants to display
up to 15 minute films. These should ideally cover applications of expert
systems and neural networks to real problems in Commerce, Industry,
Medicine, Agriculture, Government, Education, etc.
SPONSORSHIP
The initial sponsor of the ANNES'93 conference is the New Zealand
Computer Society.
REGISTRATION
The registration fees to attend the conference are:
Full time students: NZ$ 75.00
Academics,company representatives: NZ$300.00
One tutorial: NZ$ 100.00
A single day registration: NZ$ 150.00
An exhibition fee: NZ$50.00
A discount of 20% applies for advance registration which must be posted
to the secretary before 30 July 1993. A discount of NZ$50 applies to
participants who will present their accepted papers either in the oral or
in the poster session.
VENUE
The University of Otago, Dunedin, New Zealand.
ACCOMMODATION
Accommodation has been booked at St Margaret's College located right on
the Campus and 10 minutes from downtown Dunedin. The college offers well
equipped facilities including library, sports hall, music hall and
computers with E-MAIL connection. Full board (NZ$50) is available during
the conference days as well as two days before or after the conference.
Accommodation will be also booked for a range of hotels in the city.
POSTCONFERENCE EVENTS
Following the conference, delegates may like to experience the delights
of Queenstown and Central Otago. A variety of options are available with
travel plans able to be coordinated by the Dunedin Visitors Centre
(telephone +(3)4743300, Octagon, Dunedin, New Zealand). Further
information will be provided in the second call for papers.
ANNES'93 CONFERENCE CONTACTS:
PROGRAM AND CONFERENCE CHAIR
Nikola Kasabov
Tel. +(3) 479 8319, Fax. +(3) 479 8311
email: nkasabov@otago.ac.nz
Department of Information Science, University of Otago, P.O.Box 56,
Dunedin, New Zealand
(Conference program, papers, proceedings, tutorials, reviewing, invited
talks)
CHAIR OF THE ORGANIZING COMMITTEE
Martin Anderson
Tel. +(3) 479 8315, Fax. +(3) 479 8311
email: manderson@otago.ac.nz
Department of Information Science, University of Otago, P.O. Box 56,
Dunedin, New Zealand
(Sponsorship proposals, exhibition proposals, video track, business and
industry contacts)
POSTGRADUATE STUDENT SESSION
Ms. Kitty Ko
Tel. +(3) 479 8153, Fax. +(3) 479 8311, email: kittyko@otago.ac.nz
Department of Information Science, University of Otago, P.O.Box 56,
Dunedin, New Zealand
ADMINISTRATIVE SECRETARY:
Ms Gina Porteous
Tel.+(3) 479 8180, Fax. +(3) 479 8311, email:gporteous@otago.ac.nz
Department of Information Science, University of Otago, P.O. Box 56,
Dunedin, New Zealand
(Registration and all enquiries).
DEADLINES
30 April 1993 Submission of papers.
30 June 1993 Notification of acceptance.
30 July 1993 Early registration; final papers.
ANNES'93 - The First New Zealand International Two-stream Conference
on Artificial Neural Networks and Expert Systems,
24-26 November 1993, University of Otago, Dunedin, New Zealand
REPLY FORM
Please complete and send to the secretary:
Ms. Gina Porteous
Department of Information Science, University of Otago
P.O. Box 56, Dunedin, New Zealand
Tel. +(3) 479 8180, Fax. +(3) 479 8311, email: gporteous@otago.ac.nz
Name, First name:
University or company:
Mail address:
Fax: Phone: Email:
I intend to attend the conference:
I intend to submit a paper (If Yes, please give the provisional title):
Please send me the program when ready:
I intend to attend the tutorial(s): 1 ,2 ,3 ,4
I intend to exhibit a product (If Yes, please give details on a separate
sheet )
I intend to display a video film (Give details on a separate sheet please)
I intend to attend the postgraduate student session:
I intend to submit a paper to the postgraduate session (Please give the
provisional title):
Please send the ANNES'93 First Call for Papers and Participants to the
colleagues of mine at the following addresses:
------------------------------
End of ML-LIST (Digest format)
****************************************
