Machine Learning List
Tue, 19 Aug 2003 18:39:24 -0700
Machine Learning List: Vol. 15, No. 14
Tuesday, August 19, 2003
Contents
Meeting Announcements
Workshop on "Collaboration Agents: Autonomous Agents ..."
Genetic and Evolutionary Computation COnference (GECCO-2004)
IIS:IIPWM'04 - First Announcement
Career Opportunities
Bank One Job Opportunities
2004-2005 IBM Herman Goldstine Postdoctoral Fellowship
Jobs at Fair Isaac Corporation
Miscellaneous Announcements
MLJ special issue on ML and Genomics
New Book / Genetic Programming IV ...
jmlr-announce: Special Issue on Inductive Logic Programming
The Machine Learning List is moderated. Contributions should be
relevant to the scientific study of machine learning. Please send
submissions for distribution to: [EMAIL PROTECTED] For requests to be
added, removed, or to change your email address, send email to:
[EMAIL PROTECTED]
To keep mailings to a manageable size, please keep submissions brief.
For meeting announcements, do highlight the meeting Web site and the
goals of the event but omit information such as the program committee
and talk schedules. Also, only first calls for papers and change of
deadline announcements will be included. The ML List moderator
reserves the right to omit/edit submissions to meet these criteria.
----------------------------------------------------------------------
From: Undisclosed Sendor <[EMAIL PROTECTED]>
Subject: Workshop on "Collaboration Agents: Autonomous Agents ..."
Date: Fri, 1 Aug 2003 14:06:44 +0800 (CST)
CALL FOR PAPERS
Workshop on "Collaboration Agents: Autonomous Agents for Collaborative
Environments"
October 13, 2003, Halifax, Canada
http://www.cs.unb.ca/~ghorbani/ca/index.html
In conjunction with 2003 IEEE/WIC International Conference on
Web Intelligence / Intelligent Agent Technology
http://www.comp.hkbu.edu.hk/WI03
http://www.comp.hkbu.edu.hk/IAT03
Autonomous agents have long been recognised as particularly promising
tools for mundane tasks such as information seeking and
distribution. Many researchers have recognised the power of multiple
agents collaborating to achieve these and other tasks. However, in
only a few cases, have agents been utilised to bring people together
(or at least schedule them), and recent developments are producing
architectures of agents that can go further, facilitating interactions
as humans might. We believe that it is in the bringing together of
people that agents can finally realise their potential.
This workshop is intended to bring to the fore the state of the art of
research and development of agents that bring people together,
through, for example, scheduling, monitoring, or facilitating
meetings, distributing information and building societies, and
maintaining links between people whenever they can. The workshop will
not focus on, for example, the development of interface of search
agents - forums exist to bring this research to the fore. Our interest
is in the building of a community of researchers in the area to allow
the growth of a highly exciting field, one in which agents help people
come together.
Topics:
Topics of interest include, but are not necessarily limited to:
Collaborative and competitive behaviour of multiple agents
Privacy and security in collaboration agents
Conflicts, conflict resolution and negotiation
Developed, developing, or planned architectures
Technical and philosophical issues in the design of collaboration agents
Important Dates:
September 1, 2003 Deadline for submission of papers
September 11, 2003 Notification of acceptance
September 26, 2003 Final copy due
October 13, 2003 Workshop
Participation and Submissions:
Participation in this workshop is by invitation only and invitees must
be registered for the WI/IAI 2003 conferences. Also attendance is
limited. Therefore, in case that a selection becomes necessary, we
ask researchers that just want to attend the workshop without
contributing a paper to send a short email to [EMAIL PROTECTED]
expressing their particular interest in the workshop.
Submitted papers should be formatted in the style of IEEE-Computer
Society Format: http://www.computer.org/cspress/instruct.htm The page
limit for the final version is 12 pages. We only accept electronic
submissions. Please send your manuscripts (PDF format only) to the
program chairs:
After workshop activities:
Besides online and conventional proceedings a special issue of a journal
will be prepared for the resubmitted papers from this workshop.
For further details, see http://www.cs.unb.ca/~ghorbani/ca/index.html
------------------------------
From: "John Koza" <[EMAIL PROTECTED]>
Subject: Genetic and Evolutionary Computation COnference (GECCO-2004)
Date: Sat, 2 Aug 2003 12:19:35 -0700
CALL FOR PAPERS
2004 Genetic and Evolutionary Computation COnference (GECCO-2004)
June 26-30, 2004 (Saturday-Wednesday) Seattle, Washington, USA
Paper Submission Deadline: January 15, 2004
A recombination of the 13th International Conference on Genetic
Algorithms (ICGA) and the 9th Genetic Programming Conference (GP)
http://www.isgec.org/gecco-2004/
The Genetic and Evolutionary Computation Conference (GECCO-2004) will
present the latest high-quality results in the growing field of
genetic and evolutionary computation. Topics include: genetic
algorithms (GA); genetic programming (GP); evolution strategies (ES);
evolutionary programming (EP); learning classifier systems (LCS);
evolvable hardware (EH); real-world applications (RWA); artificial
life, adaptive behavior, agents, and ant colony optimization (AAAA);
biological applications (BIO); evolutionary robotics (ER);
evolutionary scheduling and routing (ESR); search based software
engineering (SBSE); Co-evolution (COEV); Artificial Immune Systems
(AIS), and other areas to be announced.
ONE CONFERENCE - MANY MINI-CONFERENCES
Each paper submitted to GECCO will be rigorously reviewed, in a blind
review process, by one of at least thirteen separate and independent
program committees specializing in various aspects of genetic and
evolutionary computation. These committees make their own final
decisions on submitted papers for their areas, subject only to
conference-wide space limitations and procedures. Keywords will be
used to help match referees to papers.
FREE TUTORIALS
The conference will include over 30 free tutorials from some of the
world's foremost experts in several topics of interest to genetic and
evolutionary computation researchers and practitioners.
WORKSHOPS
Several workshops on a variety of EC-related topics will be held
during GECCO-2004. See http://www.isgec.org/gecco-2004/ for the latest
list of topics and scheduling information. Suggest a workshop by
contacting Stefano Cagnoni: [EMAIL PROTECTED]
HOW TO SUBMIT A PAPER TO THE GECCO CONFERENCE
The deadline for ARRIVAL of submissions is THURSDAY, JANUARY 15, 2004.
See http://www.isgec.org/gecco-2004/ for details on paper and
electronic submissions, including procedures and formatting
details. The conference proceedings will be published in book form and
on CD-ROM and distributed at the conference. The GECCO review process
is "double blind," meaning that reviewers should not be able to infer
the identities of the authors of the papers that they are reviewing
(and, of course, that authors will not know the identities of their
reviewers).
Each paper MUST identify a category under which it will be
reviewed. Possible categories include:
Genetic Algorithms
Genetic Programming
Evolution Strategies and Evolutionary Programming
Learning Classifier Systems
Evolvable Hardware
Real-World Applications
Biological Applications
Evolutionary Robotics
Artificial Life, Adaptive Behavior, Agents and Ant Colony Optimization
Evolutionary Scheduling and Routing
Search Based Software Engineering
Coevolution
Artificial Immune Systems
Other categories as may be subsequently added on the web site To help
match referees to papers authors are additionally required to provide
keywords describing the content of their paper. Review criteria will
include significance of the work, novelty, clarity, writing quality,
and sufficiency of information to permit replication (if
applicable). The first-named author (or other corresponding author
designated by the authors when submitting) will be notified of
acceptance or rejection (in early March 2004). By submitting a paper,
the author(s) agree that, if their paper is accepted, they will submit
a final revised camera-ready version by the deadline for camera-ready
papers (in late March, 2004), they will register at least one author
by the deadline for camera-ready papers, and at least one author will
attend and present the accepted paper at the conference.
The material in papers must represent substantially new work that has
not been previously published by conferences, journals, or edited
books in the evolutionary computation field. GECCO permits a paper to
be submitted that is substantially similar to a paper being submitted
contemporaneously for review in another conference; however, if the
submitted paper is accepted by the GECCO conference, the authors agree
that substantially the same material will not be published by another
conference in the evolutionary computation field. (Material may be
later revised and submitted to a journal if permitted by the journal
involved.)
For further details, see http://www.isgec.org/gecco-2004/
------------------------------
From: "IIPWM Conf. Office" <[EMAIL PROTECTED]>
Subject: IIS:IIPWM'04 - First Announcement
Date: Tue, 12 Aug 2003 15:24:01 +0200
FIRST ANNOUNCEMENT:
INTELLIGENT INFORMATION SYSTEMS 2004 - IIS'04
New Trends in Intelligent Information Processing and Web Mining (IIPWM)
Zakopane, Poland, May 17-20, 2004
Conference Web page: http://iipwm.ipipan.waw.pl
The conference will have special tracks on:
- Artificial Immune Systems
- Search Engines
- Computational Linguistics
The Conference's focus will also be on the following topics:
- new computing paradigms, including, but not restricted to
biologically motivated methods, quantum computing, DNA computing,
- advanced data analysis,
- new machine learning paradigms,
- reasoning technologies,
- natural language processing,
- novelty detection,
- new optimization technologies,
- applied data mining using statistical and non-standard approaches,
- technologies for very large data bases,
- uncertainty management.
Publication:
http://iipwm.ipipan.waw.pl/2004/publication.html
Publication in the Springer Verlag Series on Advances in Soft
Computing is envisaged.
Important Dates:
http://iipwm.ipipan.waw.pl/2004/dates.html
15th October, 2002 - papers' submission deadline
8th December, 2002 - acceptance/rejection decision due
22th December, 2003 - submission of camera-ready papers
17th May, 2003 - the Conference starts
Paper Submission and Publication:
http://iipwm.ipipan.waw.pl/2004/forauthors.html
The working language of the conference is English. Only original,
unpublished papers in the aforementioned fields are invited. Authors
should submit an electronic version of full paper (up to eight pages;
source, ps and possibly pdf files) to the conference office:
[EMAIL PROTECTED] before October 15, 2003. The papers should be
organized in accordance with common scientific structure (abstract,
state of the art in the field, intention, used methodology, obtained
results and references). Papers will be refereed by an international
committee, and accepted on the basis of their scientific merit,
novelty and relevance to the conference topics. After notification of
acceptance, authors will be allowed to make a correction in accordance
with the suggestions of the reviewers and submit final camera-ready
papers. The conference proceedings will be published in the
Springer-Verlag series Advances in Soft Computing=94. Accepted papers
must be presented by author (s) personally to be published in the
conference proceedings.
The final papers are to be prepared using LaTeX. Please download the
Springer's class and some more files needed to process your
document. They are available in the file iipwm-styles.zip from the
same place as the file you are currently reading. Example of use is
contained in iipwm-example.zip.
Contact:
Conference Office: [EMAIL PROTECTED]
Institute of Computer Science,
Polish Academy of Sciences
ul. Ordona 21
01-237 Warsaw, Poland
phone: ++48 22 8362841
fax: ++48 22 8376564
For further details, see http://iipwm.ipipan.waw.pl
------------------------------
From: <[EMAIL PROTECTED]>
Subject: Bank One Job Opportunities
Date: Mon, 11 Aug 2003 10:44:22 -0400
All positions in Wilmington, DE.
1. Decision Tech Sr Analyst
This is an senior analyst (AVP) level position which will directly
support Acquisition Marketing by providing statistical modeling and
analytical support. Specifically, this individual will be responsible
for the development and implementation of statistical targeting models
which are used by Acquisition Marketing to identify likely responders
to both Bank One and its partners credit solicitations. Additionally,
this individual will assist in the development of valid statistical
test designs which will ensure the correct evaluation of a marketing
program's effectiveness and the profiling and modeling of the
program's responders. Statistical modeling will include the
development of logistic response models and cluster analyses. Any
candidate for this position must have a very strong statistical
background, thorough knowledge of relational databases, excellent
skills in SAS and SQL in a server environment and very clear
communication skills. Knowledge of direct marketing techniques and
the FUSA Prospect database is highly desirable. Additionally, this
position will have management responsibilities.
Job Requirements:
3 yrs industry experience in statistics and modeling. advanced degree
in Stat, or Econ. Statisitical target modeling, experimental test
designs, data analysis, Excellent skills in SAS and SQL in a server
environment, very clear verbal communication skills, and presentation
skills. Knowledge of direct marketing and data mining techniques is
required.
2. Decision Tech Analyst
Position Description:
This is a statistical analyst/modeling position with Bank One,
directly supporting customer marketing and retention. Specifically,
this individual will be responsible for the development and
implementation of statistical targeting models. Additionally, this
individual will assist in the development of valid statistical test
designs which will ensure the correct evaluation of a marketing
program's effectiveness and the profiling and modeling of the
program's responders. Major business functions performed by this
position include: process modeling; forecasting; data analysis;
internal consulting; vendor evaluation; proposal development; customer
behavior; experimental design; cost/benefit analysis; and operations
research.
Job Requirements:
MS in a technical field, preferably Statistics (will consider
Engineering, Math, Econometrics or Operations Research), PH.D is
preferred. Must have MS and a minimum of 2 years of experience OR a
Ph.D. Knowledge of statistical software packages (SAS, SQL,
SPSS). Good programming (e.g., C/C++) and Unix scripting skills are
desired, as is experience with statistical packages (e.g., SAS,
S-plus). Knowledge and experience developing pattern recognition and
modeling techniques (regression, neural networks, decision trees,
evolutionary algorithms, etc.) or data mining experience with large,
transactional data sets (financial services, insurance,
telecommunications, or related industries) preferred. Evidence of
leadership, initiative, productivity and teamwork preferred. Excellent
oral and written communications and interpersonal skills required.
------------------------------
From: John Langford <[EMAIL PROTECTED]>
Subject: 2004-2005 IBM Herman Goldstine Postdoctoral Fellowship
Date: Wed, 13 Aug 2003 12:41:31 -0400
I (John Langford) personally recommend this. There is no better
combination of freedom to do research and access to real problems.
The Mathematical Sciences Department of the IBM Thomas J. Watson
Research Center invites applications for its 2004-2005 Herman
Goldstine Postdoctoral Fellowship for research in mathematical and
computer sciences. Areas of active research in the department
include: algorithms; coding theory; cryptography; data mining;
dynamical systems and differential equations; economics;
high-performance computation; numerical analysis; optimization;
probability theory; statistics; and supply-chain and operations
management. Fellows interact closely with department members but are
free pursue their own research.
Candidates must have a Ph.D. after September 1999 or should receive
one before the second half of 2004. One fellowship will be awarded
with stipend between $87,000 and $107,000 (depending on area and
experience).
Applications must be received before December 20, 2003. Complete
details and the application procedure are available at
http://www.research.ibm.com/math/goldstine.html.
IBM is proud to be an equal-opportunity employer committed to
work-place diversity.
------------------------------
From: "Sirosh, Joseph" <[EMAIL PROTECTED]>
Subject: Jobs at Fair Isaac Corporation
Date: Fri, 15 Aug 2003 17:27:15 -0700
Fair Isaac Corporation (NYSE: FIC) has several open positions for
senior analytic scientists with strong backgrounds in data mining, KDD
and machine learning. We are actively recruiting for high calibre
scientists both at the senior and entry levels.
Job Responsibilities:
While they vary by position, job responsibilities typically involve
developing advanced analytical applications based on large customer
data sets and R&D into innovative customer solutions using statistical
modeling, machine learning, and AI techniques. We tackle diverse
problems such as credit risk assessment, fraud detection, text and
unstructured data analysis, optimization and decision analytics for
enterprise decision management.
Minimum Qualifications:
PhD (or MS with industry experience) in statistics, operations
research, applied math, engineering, or computer science. Demonstrated
skill with statistical packages, scripting languages, databases and
computer languages. Experience in building cutting edge data mining
solutions. Experience in developing innovative data mining algorithms
with large data sets. The following tools are relevant: SAS, SPSS,
Tcl, Perl, Python, SQL, MySQL, C, C++, Java.
Contact: Dawn Ridz at [EMAIL PROTECTED]
Fair Isaac to Interview at KDD Conference
Fair Isaac Corporation is also excited to announce that we will be
holding interviews during the 2003 KDD Conference, August 24-27th. In
addition to the several open positions for Senior Analytic Scientists,
we have an active College Recruitment Program to recruit talented
MS/PhD level talent to our San Diego, Irvine, and San Rafael, CA
offices. To be considered for an interview, please submit your resume
to HR Lead/Recruiter, Dawn Ridz at [EMAIL PROTECTED] or fax to
858-202-2056. Dawn will join our Scientific Team at the KDD Conference
in order to conduct interviews. For complete position listings, please
visit our website at www.fairisaac.com
Brief Corporate Overview: Fair Isaac Corporation (NYSE:FIC) is the
preeminent provider of creative analytics that unlock value for
people, businesses and industries. The company's predictive modeling,
decision analysis, intelligence management, decision management
systems and consulting services power more than 25 billion
mission-critical customer decisions a year. Founded in 1956, Fair
Isaac helps thousands of companies in over 60 countries acquire
customers more efficiently, increase customer value, reduce fraud and
credit losses, lower operating expenses and enter new markets more
profitably. As of August 2002, HNC Software Inc., a leading provider
of high-end analytic and decision management software, is part of Fair
Isaac.
------------------------------
From: Robert Holte <[EMAIL PROTECTED]>
Subject: MLJ special issue on ML and Genomics
Date: Sat, 2 Aug 2003 12:59:01 -0600 (MDT)
Machine Learning (MLJ) is pleased to announce publication of a
special issue on "Machine Learning in the Genomics Era".
This is freely available via the journal homepage
http://www.kluweronline.com/issn/0885-6125
Click on "Journal Contents" in the menu in the left sidebar and then,
in the right-hand column under 2003 (volume 52), select
Issue 1-2, July - August 2003
The papers in this special issue are listed below.
Also freely available are all forthcoming papers (over 20 at present).
Click on "Forthcoming Papers" in the menu in the left sidebar.
Special Issue: Machine Learning in the Genomics Era
Editorial: Methods in Functional Genomics
Paola Sebastiani, Isaac S. Kohane, Marco F. Ramoni
Relation Between Permutation-Test P Values and Classifier Error
Estimates
Tailen Hsing, Sanju Attoor, Edward Dougherty
Boosting and Microarray Data
Philip M. Long, Vinsensius Berlian Vega
Analysis and Visualization of Gene Expression Microarray Data in
Human Cancer Using Self-Organizing Maps
Sampsa Hautaniemi, Olli Yli-Harja, Jaakko Astola, Paivikki Kauraniemi,
Anne Kallioniemi, Maija Wolf, Jimmy Ruiz, Spyro Mousses,
Olli-P. Kallioniemi
Self-Organizing Latent Lattice Models for Temporal Gene Expression
Profiling
Byoung-Tak Zhang , Jinsan Yang, Sung Wook Chi
Consensus Clustering: A Resampling-Based Method for Class Discovery
and Visualization of Gene Expression Microarray Data
Stefano Monti, Pablo Tamayo, Jill Mesirov, Todd Golub
Inclusion of Textual Documentation in the Analysis of Multidimensional
Data Sets: Application to Gene Expression Data
Soumya Raychaudhuri, Hinrich SchüRuss B. Altman
On Learning Gene Regulatory Networks Under the Boolean Network Model
Harri Lahdesmaki, Ilya Shmulevich, Olli Yli-Harja
External Control in Markovian Genetic Regulatory Networks
Aniruddha Datta, Ashish Choudhary, Michael L. Bittner, Edward
R. Dougherty
------------------------------
From: "John Koza" <[EMAIL PROTECTED]>
Subject: New Book / Genetic Programming IV ...
Date: Sat, 2 Aug 2003 12:20:51 -0700
NEW BOOK
Genetic Programming IV: Routine Human-Competitive Machine Intelligence
(ISBN 1-4020-7446-8)
Published by Kluwer Academic Publishers (http://www.wkap.nl/)
Genetic programming (GP) is method for automatically creating computer
programs. It starts from a high-level statement of what needs to be
done and uses the Darwinian principle of natural selection to breed a
population of improving programs over many generations.
This new book makes 4 main points:
· GP now delivers routine human-competitive machine intelligence.
· GP is an automated invention machine.
· GP can create general solutions to problems in the form of
parameterized topologies.
· GP has delivered qualitatively more substantial results in synchrony
with the relentless iteration of Moore's Law.
The book describes 15 instances where GP has created an entity that
either infringes or duplicates the functionality of a previously
patented 20th-century inventions, 6 instances where it has done the
same with respect to post-2000 patented inventions, 2 instances where
GP has created patentable new inventions, and 13 other
human-competitive results.
The book presents the application of GP to a wide variety of problems
involving automated synthesis of controllers, circuits, antennas,
genetic networks, and metabolic pathways.
A 42-minute video overview is contained in a DVD that comes with the
book.
To read chapter 1 in PDF format, visit
http://www.genetic-programming.org/gpbook4toc.html
Additional information (including table of contents) is available at
http://www.genetic-programming.org/gpbook4toc.html
There is a 25% discount coupon in PDF format (expiring September 30,
2003) at http://www.genetic-programming.org/gp4discount25sept30.pdf.
ORDERING THE BOOK
The book can be purchased using a 25% discount coupon in PDF format
(expiring September 30, 2003) at
http://www.genetic-programming.org/gp4discount25sept30.pdf.
The book (ISBN 1-4020-7446-8) can be ordered from
Kluwer Academic Publishers
P.O. Box 358 - Accord Station
Hingham, MA 02018-0358 USA
Phone : (781) 871-6600
Toll-Free Phone: (866) 269-9527
Fax : (781) 681-9045
E-mail : [EMAIL PROTECTED]
URL: http://www.wkap.nl/
------------------------------
From: "David 'Pablo' Cohn" <[EMAIL PROTECTED]>
Subject: jmlr-announce: Special Issue on Inductive Logic Programming
Date: 18 Aug 2003 09:36:55 -0700
The Journal of Machine Learning Research (www.jmlr.org) is pleased to
announce publication of the Special Issue on Inductive Logic
Programming:
Introduction to the Special Issue on Inductive Logic Programming
James Cussens, Alan M. Frisch; pp. 413-414.
ILP: A Short Look Back and a Longer Look Forward
David Page, Ashwin Srinivasan; pp. 415-430.
Relational Learning as Search in a Critical Region
Marco Botta, Attilio Giordana, Lorenza Saitta, Michèle Sebag;
pp.431-463.
Query Transformations for Improving the Efficiency of ILP Systems
Vítor Santos Costa, Ashwin Srinivasan, Rui Camacho, Hendrik
Blockeel, Bart Demoen, Gerda Janssens, Jan Struyf, Henk
Vandecasteele, Wim Van Laer; pp. 465-491.
Learning Semantic Lexicons from a Part-of-Speech and Semantically
Tagged Corpus Using Inductive Logic Programming
Vincent Claveau, Pascale Sébillot, Cécile Fabre, Pierrette
Bouillon; pp 493-525.
The papers in this issue are available electronically at
http://www.jmlr.org in PostScript and PDF formats. The papers of
Volumes 1, 2 and 3 are also available electronically from the JMLR
website, and in hardcopy from the MIT Press; please see
http://mitpress.mit.edu/JMLR for details.
------------------------------
End of ML-LIST Digest Vol 15, No. 14
************************************