Copy Link
Add to Bookmark
Report
Machine Learning List Vol. 6 No. 31
Machine Learning List: Vol. 6 No. 31
Sunday, Decemeber 18, 1994
Contents:
MLC++: Machine Learning Utilities Available
disjunctive concept learning
AI/Stats
Job announcement: University of Sydney
Jobs for posting: UNIVERSITY OF ABERDEEN
ECML-95 Registration Form
1st Intl Conference on Knowledge Discovery and Data Mining (KDD-95)
IJCAI-95 Workshop CFP: Adaptation and Learning in Multiagent 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>
URL- http://www.ics.uci.edu/AI/ML/Machine-Learning.html
----------------------------------------------------------------------
Date: Sat, 3 Dec 1994 23:31:40 +0800
From: Ronny Kohavi <ronnyk@cs.stanford.edu>
Subject: MLC++: Machine Learning Utilities Available
MLC++ Utilities 12/3/94
_______________
MLC++ is a Machine Learning library of C++ classes being developed at
Stanford. More information about the library can be obtained at URL
http://robotics.stanford.edu:/users/ronnyk/mlc.html.
We are now releasing the object code for some utilities written using MLC++.
These will run on Suns, either on SunOS or Solaris.
Included in the current release are the following induction algorithms:
1. Majority (baseline).
2. Basic ID3 for inducing decision trees. The output can be sent
to a mail server to get a postscript picture of the resulting
tree. Very useful for looking at the final tree and for teaching.
3. Basic nearest neighbor.
4. Decision Table.
5. Interface to C4.5 (for utilities below).
6. Feature subset selection : wraps around any of the above and
selects a good subset of the features, usually improving
performance and comprehensibility.
Utilities released are:
1. Cross validation : cross validate a file and any of the above induction
algorithms. Allows regular or stratified CV.
You can also generate the cross validation files to compare
your own induction algorithm.
2. Learning curve : generate a learning curve for any of the above
induction algorithms.
3. Project : project the data onto a subset of attributes.
4. Convert : convert nominal attributes to unary encoding or binary
encoding.
Quick starter guide:
The MLC++ utilities are accessible by anonymous ftp to
starry.stanford.edu:pub/ronnyk/mlc/
There are currently two kits, one for Solaris (MLCutil-solaris.tar.Z)
and one for SunOS (MLCutil-sunos.tar.Z).
cd <directory>
zcat <kit-name> | tar xvf -
where <directory> is the directory under which the mlc directory will
be built (e.g., /usr/local), and <kit-name> is the kit appropriate
for your machine.
The documentation is in utils.ps.
The environment variable MLCDIR must be set to the directory where
the utilities are installed.
Databases in the MLC++ format, which is very similar to C4.5 format
can be found in starry.stanford.edu:pub/ronnyk/mlc/db.
Most datafiles are converted from the repository at UC Irvine.
Questions or help requests related to the utilities should be
addressed to mlcpp-help@CS.Stanford.EDU
Ronny Kohavi (ronnyk@CS.Stanford.EDU, http://robotics.stanford.edu/~ronnyk)
------------------------------
Date: Wed, 14 Dec 94 16:30:23 -0500
From: Larry Hunter <hunter@work.nlm.nih.gov>
Subject: disjunctive concept learning
I've been doing some experiments in multistrategy learning, and I've been
surprised at how poorly the ml techniques I've been using (lfc++, c4.5 & NNs
trained with conjugate gradient descent backprop) do a learning disjunctive
concepts.
For example, none of the learners do very well at learning the concept "any
three consecutive bits on" in a length 9 bit string. The neural nets do the
best, but are impractical for similar but larger problems. There must be
symbolic learners that are good at disjunctive concepts, but a quick search
of the literature (well, of the MLj) didn't turn up anything clearly
relevant. With all the CoLT talk of k-DNF learning, I would have thought
there would be a good one somewhere.
Does anyone have any suggestions for algorithms, or, better yet, ftp-able
programs that do well at these kinds of concepts?
Larry
hunter@nlm.nih.gov
------------------------------
Date: Thu, 8 Dec 1994 10:22:13 +0600
From: "Douglas H. Fisher" <dfisher@vuse.vanderbilt.edu>
Subject: AI/Stats
This is a reminder that the Fifth International
Workshop on Artificial Intelligence and Statistics
will be held Jan. 4-7, 1995 in Ft. Lauderdale, FL.
Information regarding schedule, hotel, registration,
and tutorials can be found at:
http://www.vuse.vanderbilt.edu/~dfisher/ai-stats-call
Doug Fisher
General Chair
------------------------------
Date: Tue, 29 Nov 1994 17:57:58 +1100
From: Ross Quinlan <quinlan@ml2.cs.su.oz.au>
Subject: Job announcement: University of Sydney
Postdoctoral Research Associate (Fixed Term)
Inductive Learning Project
University of Sydney, Australia
This project, funded by the Australian Research Council, involves the
development and evaluation of computation-intensive empirical learning
methods. Topics of particular interest are first-order relational
learning (ILP), learning to approximate functions, classification,
hybrid learning methods, and applications.
Duties will involve all aspects of the project: constructing and
modifying programs, planning and running experiments, analysing
results, assisting in the preparation of papers, and taking part in
discussions and seminars.
An appointment for up to three years will be available for commencement
early in 1995. Applicants should have recently completed a PhD in
Artificial Intelligence (preferably with publications in Machine
Learning). Excellent C programming skills and communication skills
(both written and oral) are essential. Familiarity with concepts and
techniques of Machine Learning and experience conducting and analysing
experiments would be particularly advantageous.
Salary: A$37,345 -- A$40,087 per annum (A$1 = US$0.75 approx).
Applications should include a c.v. and the names, addresses, telephone
and fax numbers of two referees. Applications should be sent to
Prof. J.R. Quinlan
Basser Department of Computer Science
Madsen Building F09
University of Sydney
Sydney Australia 2006
Closing date for applications: 9th January 1995.
Please contact Ross Quinlan (quinlan@cs.su.oz.au) if you need any
further information.
------------------------------
From: Derek Sleeman <sleeman@csd.abdn.ac.uk>
Date: Sat, 10 Dec 1994 22:30:49 GMT
Subject: Jobs for posting: UNIVERSITY OF ABERDEEN
UNIVERSITY OF ABERDEEN
LECTURERS IN COMPUTING SCIENCE (2)
Pounds 14,756- Pounds 25,735 p.a.
Applications are invited for two new posts in the
Department of Computing Science. The appointees will have
good teaching skills applicable at undergraduate and
postgraduate level, as well as an established record of
research in the academic or industrial sectors. This could
be in any area of Computing Science, but, ideally, will
complement existing research in Artificial Intelligence and
Databases. Both posts are available immediately with the
second being a five year appointment. For an informal
discussion, please contact Dr Jim Hunter, (telephone 01224
272295, email jhunter@csd.abdn.ac.uk).
Application forms and further particulars are available
from Personnel Services, University of Aberdeen, Regent
Walk, Aberdeen AB9 1FX, telephone 01224 272727), quoting
reference number FCS 021A. A 24 hour answering service is
in operation. Closing date: 6 January 1995 (the University
will be closed for the period 24 December - 3 January)
An Equal Opportunities Employer.
Aberdeen University is set within easy reach of some of
Britain's most attractive sea coast, mountains and
agricultural country, and is also at the hub of a busy
commercial centre which benefits from excellent air, rail
and road links. The University of Aberdeen is established
to provide Higher Education and to carry out related
research.
EXTRACT FROM FURTHER PARTICULARS
The full Further Particulars can be found at
http://www.csd.abdn.ac.uk/people/vacancies.html
which has a link to the home page of the Department.
THE DEPARTMENT
The Department is housed in modern refurbished
accommodation in the Meston Building at Old Aberdeen.
The current staff (Autumn 1994) consists of 2 Professors, 2
Senior Lecturers, 7 Lecturers, 2 Computer Officers and a
Teaching Assistant. Two Secretaries and an Accounts Clerk
provide support for the Department.
The Computing facilities in the Department are excellent,
with a mixture of SUN-4 workstations and X-terminals served
by SUN-4 file and computer servers for staff and students.
Classrooms of X-terminals, IBM PCs and MACs are also
available for undergraduate teaching.
The software used in the Department for research and
teaching includes: PROLOG, CHIP, LISP, POPLOG, Smart
Elements, CLIPS, HIPS, Miranda, C, C++, Occam-2, Smalltalk,
and SYBASE.
The University Computing Centre is responsible for
providing all the networking facilities on campus, and in
particular, provides access to the SuperJANET network which
in turn allows access to several international gateways.
The Department has particular expertise in AI and Databases
and there is a substantial focus on these areas. It
received a grade 4 in the last Research Assessment
Exercise. In addition to members of academic staff there
are a number of research students with interests in this
general area. Interdisciplinary research is encouraged, as
will be seen from the list below.
CURRENT RESEARCH
AI support for Engineering Design, Off-Line Programming of
Robots; Geometric Reasoning; Solid Modelling Systems;
Uncertainty Reasoning, Application of Formal Methods to
Parallel and Real-Time Programming. (Mrs Pat Fothergill
and Dr Robert Holton)
Object-Oriented Knowledge Bases; Automatic Programming;
Constraints and Active Rules in Databases; Intelligent
Database Search; Interactive Graphic Retrieval of Protein
Structure; Multi-Databases and Schema Integration
(Professor Peter Gray and Dr Graham Kemp)
AI and Medicine; Qualitative Reasoning (Dr Jim Hunter)
Computer Vision; Recognition of Human Faces (Dr Roly
Lishman)
Knowledge Base Refinement; Knowledge Base Validation and
Verification; Aids to help Scientists Refine/Reformulate
Theories; Machine Discovery (Professor Derek Sleeman, Dr
Pete Edwards, and Dr Alun Preece)
Goal-directed Knowledge Acquisition and Machine Learning
(Professor Derek Sleeman)
Intelligent Software Agents, Multiagent Systems (Dr Pete
Edwards and Dr Alun Preece)
TEACHING
Undergraduate Programmes:
In common with the majority of Scottish Universities,
Aberdeen has a four-year undergraduate Honours degree. The
Department currently offers a number of BSc degree
programmes:
BSc Single Honours
Computing Science
Computing Science (Artificial Intelligence)
Computing Science (Business Computing)
Computing Science with French or with
German or with Spanish
BSc Joint Honours Computing Science and
Engineering or Mathematics
or Psychology or Statistics
The rationale for the Honours degrees is to teach
programming and computer-based problem solving in some
depth in the first year. The syllabus in the second and
third years covers all major topics in Computer Science
(Programming Languages, Operating Systems, Theory,
Hardware, Artificial Intelligence) and the fourth year
offers a series of topics which relate to the Department's
current research activities together with a substantial
project.
The modular structure of undergraduate teaching means that
courses are open to all students (timetable permitting),
and students are not committed to a particular Honours
programme until the third year of their career.
MSc in Applied Artificial Intelligence:
This well-established MSc programme is a "specialist"
course for graduates in Computer Science or those with a
substantial background in the subject. Students completing
this course have a strong working knowledge of the
techniques and tools of Knowledge Engineering, and are well
placed to take up posts in industry or to proceed to
research. Major components of this course are the
Knowledge Engineering workshop, held in the second term and
a project during the Summer. In 1994/95 the course
attracted 27 students, several of whom are undertaking
industrial projects.
THE POSTS
These two new posts have been created in response to the
increasing numbers of students in Computing Science as well
as the wish to consolidate the Department's research
record. We are therefore looking for candidates with
established research achievements in the academic or
industrial sectors who will be able to contribute to
research, teaching and administration within the
Department. The only restriction regarding areas of
expertise with Computer Science or Artificial Intelligence
is that the work of the appointees should complement
current research in the Department:
Machine Learning
Scientific Discovery
Databases and Logic Programming
Verification of Knowledge Bases
Distributed AI
Qualitative and Temporal Reasoning
Robotics
AI & Engineering Design
Computer Vision
AI in Molecular Biology and Medicine.
Applicants should have completed a PhD degree, with a
publication record in internationally recognised
conferences or journals. Applicants without a PhD will be
considered on the basis of equivalent research experience,
especially if they have compensating publications.
The posts will be tenable from 1 January 1995 or as soon as
possible thereafter.
SALARY
The first post is permanent and will be on the Lecturer
scale (Pounds 14,756 - Pounds 25,735 p.a.). The second
post is available for 5 years and will be on the Lecturer A
scale (Pounds 14,756 - Pounds 19,326 p.a). Placement on
the scales will be according to qualifications and
experience. Please make it clear on your application
whether you wish to be considered for both posts or whether
you wish to be considered only for the permanent position.
APPLICATION PROCEDURE
Candidates who require further details, or who would like
to visit the Department for an informal discussion should
contact:
Dr Jim Hunter, Head of the Department of Computing Science,
University of Aberdeen, Meston Building, Aberdeen AB9 2UE,
(telephone 0224 272287; email jhunter@csd.abdn.ac.uk)
or
Professor Derek Sleeman (telephone 0224 272288, email
sleeman@csd.abdn.ac.uk).
An Employment Record Form should be completed and returned,
together with a CV (four copies of each) to the Personnel
Office, University of Aberdeen, Regent Walk, Aberdeen AB9
1FX.
The telephone number for any other queries is (0224)
273500.
The closing date for the receipt of applications is 6
January 1994 (please note that the University will be
closed for the period 24 December - 3 January inclusive).
------------------------------
Date: Tue, 13 Dec 1994 15:40:05 +0200
From: Account for mlt meeting <ecml-95@ics.forth.gr>
Subject: ECML-95 Registration Form
ECML - 95
8th European Conference on Machine Learning
25-27 April 1995, Heraklion, Crete, Greece
MLnet FWS - 95
MLnet 3rd Familiarization Workshop Series
28-29 April 1995, Heraklion, Crete, Greece
REGISTRATION FORM
___________________
Please make certain that this form is received by the 17th of February 1995
along with payment by (please use FAX or regular mail):
Ms. Maria Prevelianaki
ECML-95 Secretary
Institute of Computer Science (ICS)
Foundation for Reasearch and Technology (FORTH)
P.O Box 1385
711 10 Heraklion, Crete, Greece
Tel.: +30-81-391604, 391600
Fax : +30-81-391601
E-mail: ecml-95@ics.forth.gr
NAME: ___________________________________________________________________
AFFILIATION: ____________________________________________________________
FULL ADRESS: ____________________________________________________________
_________________________________________________________________________
_________________________________________________________________________
TEL:_____________________________________________________________________
FAX:_____________________________________________________________________
E_MAIL:__________________________________________________________________
Registration fee: 50000 drs. before February 17, 1995
(ECML 95) 58000 drs. before April 7, 1995
69000 drs. after April 7, 1995 Fee: ________ drs.
Registration fee: 21000 drs. before February 17, 1995
(MLnet FWS 95) 25000 drs. after April 7, 1995 Fee(*): ______ drs.
(*) If you have been awarded an MLnet bursary for MLnet FWS-95 please
indicate your bursary reference number: __________
To obtain an MLnet bursary application form please contact:
Davide Roverso (MLnet Admin.) Tel: +44-1224-272304
Dept. of Computing Science Fax: +44-1224-273422
University of Aberdeen E_mail: mlnet@csd.abdn.ac.uk
ABERDEEN, AB9 2UE
Scotland, UK
Note that MLnet bursary are normally reserved to members of MLnet nodes.
Hotel Information: We have secured a limited number of rooms in various
hotels inside Heraklion:
HOTEL CLASS SINGLE DOUBLE
GALAXY A Lux 19200 20500
GALAXY A 15300 16500
ASTORIA A 15300 16500
LATO C 9600 12800
EL_GRECO C 9000 11700
Please indicate your preference:
1st preference : _________________________(single/double)
2nd preference : _________________________(single/double)
3rd preference : _________________________(single/double)
Specify with whom you wish to share the room: _________________________
(if applicable)
Please include the amount that corresponds to the most expensive preference.
Excess funds will be credited to your amount. Hotel reservation cannot be
refunded.
ECML-95 Registration fee: _________________________ drs.
One night accommodation advance payment: _________________________drs.
MLnet FWS Registration fee: _________________________ drs.
Arrival:______________________ April 1995 Flight: ___________________
Departure: ___________________ April 1995 Flight: ___________________
Total number of nights for which you need a reservation:___________________
Conference Dinner: 8000 drs. (optional) ___________________
Additional person fee : 12000 drs.
(includes reception and Conference Dinner, optional) ___________________
TOTAL AMOUNT: ___________________
Method of payment:
* Swift funds to ERGOGRAA, ERGOBANK S.A, Heraklion, Crete, Greece, to
ECML-95 account.
* Or send a bank cheque payable to ECML-95 and drawn on ERGOBANK S.A.
Cheques should be sent to Maria Prevelianaki.
* Personal cheques will not be accepted.
* If you use a credit card please sign the attached authorization form:
Credit card (VISA/MASTERCARD/AMERICAN EXPRESS). Please fill in:
I authorize to charge my card the amount of ___________________ drs.
Name:__________________________________________________________
Card number: ___________________ Exp. date:___________________
Signature: _____________________ Date: _______________________
Cancellation Policy:
Hotel deposit generally cannot be refunded.
Registration fee, accompanying person and dinner participation will be
refunded minus Bank and related processing expenses.
Travel Agency:
KATREA Travel (Mr. George Alexakis) handles the administration of hotels
and other Conference matters. Participants may wish too contact KATREA
for further tourist information.
Adress: Pediados 3, P.O Box 1353, 712 01 Heraklion, Greece.
Tel: +30-81-281749, 391918-9
Fax: +30-81-281779
MLNet FWS Workshops :
A) Knowledge Level Modelling and Machine Learning
Please contact:
Dieter Fensel
fiensel@swi.psy.uva.nl
+31 20 525 6791 (voice)
+31 20 525 6896 (fax)
B) Learning Robots
Please contact:
Michael Kaiser
kaiser@ira.uka.de
+49 721 608 4051 (voice)
+49 721 606 740 (fax)
C) Statistics, Machine Learning, and Discovery in Data Bases
Gholamreza Nakhaeizadeh
nakhaeizadeh@dbag.ulm.DaimlerBenz.COM
+49 731 505 2860 (voice)
+49 731 505 4210
To participate in MLNet FWS you should get approval from the workshop organiser
and also notify MLNet Office (Mr. Davide Roverso).
I have submitted a paper to the A / B / C workshop (delete as appropriate)
I would like to attend workshop A / B / C (delete as appropriate)
------------------------------
Date: Fri, 16 Dec 94 09:37:05 PST
From: "Padhraic J. Smyth" <pjs@aig.jpl.nasa.gov>
Subject: 1st Intl Conference on Knowledge Discovery and Data Mining (KDD-95)
The First International Conference on
Knowledge Discovery and Data Mining (KDD-95)
--------------------------------------------
Montreal, Canada, August 20-21, 1995
====================================
Sponsored by AAAI and in Cooperation with IJCAI, Inc.
Co-located with IJCAI-95.
Knowledge Discovery in Databases (KDD) and Data Mining are areas of common
interest to researchers in machine learning, machine discovery, statistics,
intelligent databases, knowledge acquisition, data visualization, high
performance computing, and expert systems. The rapid growth of data and
information created a need and an opportunity for extracting knowledge from
databases, and both researchers and application developers have been
responding to that need. KDD applications have been developed for
astronomy, biology, finance, insurance, marketing, medicine, and many other
fields. Core problems in KDD include representation issues, search
complexity, the use of prior knowledge, statistical inference, and
algorithms for the analysis of massive amounts of data both in size and
dimensionality.
Due to strong demand for participation and the growing demand for formal
proceedings, it has become necessary to change the format of the previous
KDD workshops to a conference with open attendance. This conference will
continue in the tradition of the 1989, 1991, 1993, and 1994 KDD workshops
by bringing together researchers and application developers from different
areas, and focusing on unifying themes such as the use of domain knowledge,
managing uncertainty, interactive (human-oriented) presentation, and
applications. The topics of interest include:
Foundational Issues and Core problems in KDD
Database Mining Tools and Applications
Computationally Efficient Search for Structure in Data
Interactive Data Exploration and Discovery
Knowledge Representation Issues in KDD
Data and Knowledge Visualization
Data and Dimensionality Reduction
Prior Domain Knowledge and Re-use of Discovered Knowledge
Statistical and Probabilistic Aspects of KDD
Dependency Models and Inference
Machine Learning/Discovery Algorithms for Large Databases
Managing Model Selection and Model Uncertainty
Assessment of Model Predictive Performance
Integrated Discovery Systems and Theories
Parallel techniques for data management and search
Security and Privacy Issues in Machine Discovery
This list of topics is not intended to be exhaustive but an indication of
typical topics of interest. Prospective authors are encouraged to submit
papers on any topics of relevance to Knowledge Discovery and Data Mining.
We also invite working demonstrations of discovery systems. The conference
program will include invited talks, a demo and poster session, and panel
discussions. Active discussion format will be encouraged to maintain the
workshop feel that previous participants found valuable and constructive.
The conference proceedings will be published by AAAI. As in previous KDD
Workshops, a selected set of KDD-95 papers will be considered for
publication in journal special issues and as chapters in a book.
PAPER SUBMISSION INFORMATION:
Please submit 5 *hardcopies* of a short paper (a maximum of 9 single-spaced
pages not including cover page but including bibliography, 1 inch margins,
and 12pt font) by March 3, 1995. A cover page must include author(s) full
address, E-MAIL, a 200 word abstract, and up to 5 keywords. This cover page
must accompany the paper. IN ADDITION, an electronic version of the cover
page MUST BE SENT BY E-MAIL to kdd95@aig.jpl.nasa.gov by March 3, 1995.
Please mail the papers to : KDD-95
AAAI
445 Burgess Drive
Menlo Park, CA 94025-3496
U.S.A.
send e-mail queries regarding submissions logistics to: kdd@aaai.org
******** I m p o r t a n t D a t e s **********
** Submissions Due: March 3, 1995 **
** Acceptance Notice: April 10, 1995 **
** Camera-ready paper due: May 12, 1995 **
*************************************************
CONTACT INFORMATION:
Please send KDD-95 conference registration and related inquiries to:
KDD-95
American Association for Artificial Intelligence (AAAI)
445 Burgess Drive Menlo Park, CA 94025-3496. U.S.A.
Phone: (+1 415) 328-3123; Fax: (+1 415) 321-4457 Email: kdd@aaai.org
Please send technical program related queries to Program Co-Chairs:
Usama M. Fayyad Ramasamy Uthurusamy
Machine Learning Systems Group Computer Science Department, AP/50
Jet Propulsion Lab M/S 525-3660 General Motors Research, Bldg 1-6
California Institute of Technology 30500 Mound Road, Box 9055
Pasadena, CA 91109 Warren, MI 48090-9055
U.S.A. U.S.A.
(+1 818) 306-6197 Phone (+1 810) 986-1989 Phone
(+1 818) 306-6912 FAX (+1 810) 986-9356 Fax
Email : kdd95@aig.jpl.nasa.gov
Please send KDD-95 Publicity and related inquiries to:
Padhraic Smyth (KDD-95) email: kdd95@aig.jpl.nasa.gov
Jet Propulsion Laboratory, California Institute of Technology
4800 Oak Grove Drive, Pasadena, CA 91109 U.S.A.
Phone: (+1 818) 306-6422 Fax: (+1 818) 306-6912
Inquiries about KDD-95 sponsorship and industry participation to:
Gregory Piatetsky-Shapiro, e-mail: gps@gte.com
GTE Laboratories, MS-45 tel: 617-466-4236
40 Sylvan Road fax: 617-466-2960
Waltham MA 02154-1120 USA URL: http://info.gte.com/~kdd/
------------------------------
Date: Fri, 16 Dec 1994 17:42:35 -0600
From: Sandip Sen <sandip@kolkata.mcs.utulsa.edu>
Subject: IJCAI-95 Workshop CFP: Adaptation and Learning in Multiagent Systems
IJCAI-95 Workshop
on
Adaptation and Learning in Multiagent Systems
August 21, 1995
Workshop Description
Coordination of the activities of multiple agents, whether selfish or
cooperative, is essential for the viability of any system in which multiple
agents share resources. Learning and adaptation are invaluable mechanisms
by which agents can evolve coordination strategies that meet the demands of
the environments and the requirements of individual agents.
Researchers in the field of Distributed Artificial Intelligence have thus
far mainly concentrated on developing coordination off-line that can then
be used by agents to coordinate their activities. These pre-fabricated
coordination strategies can quickly become inadequate if the system
designer's model of the world is incomplete/incorrect or if the environment
in which the agents are situated can change dynamically. Coordination
strategies that incorporate learning and adaptation components will be more
robust and effective in these more realistic scenarios.
Researchers in machine learning and adaptive systems have been addressing
issues concerned with learning and adapting from past experience,
observation, failures, etc. Whereas most of these research have focused on
techniques for acquisition and effective use of problem solving knowledge
from the viewpoint of a single autonomous agent, a few recent
investigations have opened the possibility of application of some of these
techniques in multiagent settings. Most of these recent results, however,
use existing learning techniques to show that individual agents can respond
to the uncertainties inherent in the environment and/or uncertainties
imposed by the behavior of other agents.
The goal of this workshop is to focus on research that will address unique
requirements for agents learning and adapting to work in the presence of
other agents. Recognizing the applicability and limitations of current
machine learning research as applied to multiagent problems as well as
developing new learning and adaptation mechanisms particularly targeted to
these class of problems will be of particular relevance to this workshop.
We would particularly welcome new insights into this class of problems from
other related disciplines, and thus would like to emphasize the
inter-disciplinary nature of the workshop.
Topics of interest
Among others, papers of the following kind are welcome:
1) Benefits of adaptive/learning agents over agents with fixed behavior
in multiagent problems.
2) Exploration of the applicability of case-based, explanation-based,
and inductive learning systems in novel multiagent problems.
3) Characterization of learning and adaptation methods in terms of modeling
power, communication abilities, knowledge requirement, processing abilities
of individual agents.
4) Use of multiple learning and adaptation strategies by agents to meet the
diverse requirements of coordination in multiagent settings.
5) Developing learning and adaptation strategies for environments with
cooperative agents, selfish agents, partially cooperative (will cooperate
only if individual goals are not sacrificed) and for environments that can
contain mixture of these types of agents.
6) Analyzing and constructing algorithms that guarantee convergence and
stability of group behavior.
7) Analyzing effects of knowledge acquisition mechanism on responsiveness
of agents or groups to addition/deletion of other agents from the
environment.
8) Study of adaptive behavior in team games, where one group of cooperative
agents are pitted against another group of cooperative agents.
9) Inter-disciplinary research on multi-agent learning and adaptation
(including, but not limited to, research in organizational theory,
psychology, sociology, and economics).
10) Description of practical multiagent learning systems that solves
specific tasks with intelligent agents.
Workshop participation
Participation will be by invitation only, and will be limited to
approximately 35 people.
Submission Requirements:
Those who wish to attend the workshop should submit either: 1) a brief
statement of interest (1 page) which should include a short description of
own previous work related to the topic of the workshop including references
of relevant published papers.; or 2) those who wish to present current
research at the workshop should submit an extended abstract (no longer than
6 pages) focusing on the main contribution of the work in preference to
introductory material, literature review, etc. Please include a list of
keywords (e.g, group learning, reactive agents, evolutionary strategies,
etc.), the authors' electronic and physical address information, and
indicate if you would like to display a poster at the workshop.
Postscript versions of statements of interests or extended abstracts should
be submitted electronically to sandip@kolkata.mcs.utulsa.edu by March 13,
1995.
Submissions and questions regarding this workshop can be directed to:
Sandip Sen
Department of Mathematical & Computer Sciences,
University of Tulsa,
600 South College Avenue,
Tulsa, OK 74104-3189.
OFFICE: 918-631-2985
FAX: 918-631-3077.
e-mail: sandip@kolkata.mcs.utulsa.edu
Important Dates
Deadline for submission of papers: March 13, 1995
Notice of acceptance to participants: April 3, 1995
Camera-ready papers due: April 21, 1995
Workshop date: August 21, 1995
Organizational details
All workshop participants are required to register for the main IJCAI
conference. Each participant in the workshop will be charge a fee of
$50 in addition to the normal IJCAI-95 conference registration fee.
Participants will be selected by the workshop organizers after reviewing
all submissions. Preference will be given to researchers submitting
research papers to the workshop, but we also expect to be able to select a
number of from authors of submitted statement of interests who can
contribute significantly to the discussion in the workshop.
Further information about IJCAI-95 and related activities can be obtained
from the IJCAI home page at http://ijcai.org.
------------------------------
End of ML-LIST (Digest format)
****************************************
