Machine Learning List: Vol. 16, No. 3
Machine Learning List <[email protected]> Sat, 7 Feb 2004 09:31:36 -0800
| Newsgroups | gmane.comp.ai.machine-learning |
|---|---|
| Message-ID | <[email protected]> |
Machine Learning List: Vol. 16, No. 3
Saturday, Feburary 7, 2004
CONTENTS
CALLS FOR PAPERS/PARTICIPATION
Special Issue in Mining Graphs, Trees and Sequences
AAAI Workshop on Semantic Web Personalization
4th International Cognitive Robotics Workshop
Learning and Self-Adapting Agents (IEEE/WIC/ACM WI-IAT'04)
CEC 2004: Application of Cultural Algorithms in Industry and Engineering
CEC 2004: Learning by Estimating Distributions in Evolutionary ...
CEC 2004: Evolutionary Scheduling
CEC 2004: Evolutionary Computing in the Process Industry
CEC 2004: Recent Developments in Artificial
CEC 2004: EC in the Optimisation of Semiconductor Manufacturing ...
WCCW2004 Call for Papers: First International Workshop on Web
PSMP3 Workshop: Knowledge Representation and Acquisition for ...
First Workshop ROC Analysis in AI
KDNet Symposium on Knowledge-Based Services for the Public Sector
Algorithmic Learning Theory 2004; Discovery Science 2004
Evolutionary Computation in Industry (ECI-2004) track at GECCO-2004
Late Breaking Papers at GECCO 2004
ICML competition and workshop on Physiological Data Modeling
Call for Workshop Proposals (IEEE ICDM'04)
Computational Creativity workshop - ECCBR 04
Net.ObjectDays 2004
ITS 2004 Call for Workshop Proposals
2004 Proposal" in the Subject: line. We look forward to them!
Swarm Intelligence and Patterns (SIP'04)
WEBSA2004: 2nd Int'l Workshop on Web Based Systems and Applications ...
OTHER MEETING ANNOUNCEMENTS
ICCS Deadline Extension for Abstract Submission
MobiQuitous 04: Extended paper submission deadline
CAREER OPPORTUNITIES
Postdoc in vision/neuroscience in University College London
R&D jobs in watermarking, biometrics, HCI, medical imaging, image...
MISCELLANEOUS ANNOUNCEMENTS
Advanced Course in Computational Neuroscience 2004
What is Thought?: Book announcement
ESSLLI 2004: Preliminary Announcement
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/participation
and brief change of deadline announcements will be included. The ML
List moderator reserves the right to omit/edit submissions to meet
these criteria.
----------------------------------------------------------------------
From: Takashi Washio <[email protected]>
Subject: Special Issue in Mining Graphs, Trees and Sequences
Date: Mon, 26 Jan 2004 17:28:10 +0900
Call for Papers of Journal Special Issue and Book
in Mining Graphs, Trees and Sequences (MGTS)
Special Issue in Fundamenta Informaticae
Guest Editors
Luc De Raedt, Professor, University of Freiburg, Germany
Takashi Washio, Associate Professor, Osaka University, Japan
Joost N. Kok, Professor, Leiden University, The Netherlands
Fundamenta Informaticae http://fi.mimuw.edu.pl/index.html
Outline of Journal Special Issue
Ever since the early days of machine learning and data mining, it has
been realized that the traditional attribute-value and item-set
representations are too limited for many practical applications in
domains such as chemistry, biology, network analysis and text
mining. This has triggered a lot of research on mining and learning
within alternative and more expressive representation formalisms such
as computational logic, relational algebra, graphs, trees and
sequences. Whereas there have been a large number of workshops devoted
to multi-relational data mining and inductive logic programming as
well as applications of intermediate representations in
e.g. ontologies, bioinformatics, XML-data, text-mining, there has, to
the best of our knowledge, not been any workshops specifically devoted
to foundational issues in intermediate representations. Under this
consideration, the following workdshop has been organized to bring
together researchers interested in mining and learning within graphs,
trees and sequences. The workshop was extremely successfull, and more
than 40 researchers participated.
First International Workshop on Mining Graphs, Trees and Sequences
(MGTS-2003) (In conjunction with ECML/PKDD-2003)
http://www.ar.sanken.osaka-u.ac.jp/MGTS-2003CFP.html
On the success of MGTS-2003 workshop, we are pleased to announce Call
For Papers of Journal Special Issue in Fundamenta Informaticae on the
topic of Mining Graphs, Trees and Sequences (MGTS). We are also
planning a book edition of the special issue.
The authors who presented their work in MGTS-2003 workshop are welcome
to submit their full paper versions. The call for paper is not limited
to the authors in MGTS-2003. We strongly encourage other researchers
to submit their papers following the scope described bellow. All
submitted papers will be equivalently reviewed in terms of relevance,
originality, significance and presentation.
Scope and Motivation
The state-of-the-art of data mining is that attribute-value and
item-set representations lie at one extreme end of the spectrum, and
multi-relational data mining and inductive logic programming at the
other end. The middle is occupied by traditional data structures
employed throughout the field of computer science. These include
graphs, trees and sequences (or strings). The motivation for using
such representations is that they are 1) more expressive (and
therefore more widely applicable) than flat representations, and 2)
potentially more efficient than multi-relational learning and mining
techniques. At the same time, the data structures of graphs, trees and
sequences are among the best understood and most widely applied
representations within computer science. Thus these representations
offer ideal opportunities for developing interesting contributions in
data mining and machine learning that are both theoretically
well-founded and widely applicable.
It is precisely the goal of this special issue to bring together
researchers interested in mining and learning within graphs, trees and
sequences. We believe it is the right time to have such a journal
special issue and a book because of the increasing interest in the
role of such data structures, which is in turn motivated by the many
interesting application domains. Indeed, the total number of papers
related to graph and tree mining in SIGMOD, SIGKDD, IJCAI/AAAI, ICML,
ECML/PKDD and IEEE ICDM was 10 in 2001 and their number inceased to 18
in 2002. Along this line, the First International Workshop on Mining
Graphs, Trees and Sequences (MGTS-2003) was held in conjunction with
ECML/PKDD-2003 in September, 2003. More than 20 papers have been
submited, and 9 papers were selected for the presentation. The
research activity in MGTS field is significantly increasing.
Topics and goals
We are looking for contributions related to graph, tree and sequence
structure mining and learning. More specifically, the special issue
will focus on the following topics:
* Efficiency issues in graph, tree and sequence mining and learning
* Identifying interesting subclasses that can efficiently be mined or
learned
* Basic princinciples of graph, tree and sequence mining
* Analysis of the complexity of graph, tree and sequence mining
* Applications to real world problems in e.g., biology, chemistry,
XML, etc.
* Relationship of graph, tree and sequence mining to other techniques
* Any other result relevant to graph, tree and sequence mining.
Research works presenting theoretical results, basic research,
perspective solutions and practical developments are welcomed,
provided that they address the topic of the special issue.
Submission guidelines
Please follow the standard guideline on paper format of Fundamenta
Informaticae described in the following URL:
http://fi.mimuw.edu.pl/submissions.html
Authors are requested to email a title and a five line abstract in
plain text as early as possible to facilitate organization.
A five line abstract submissions : as early as possible
but at least before 1/March/2004
Deadline for paper submissions : 19/March/2004
Notification to authors : 19/April/2004
Tentative
(Deadline for Reviced Paper Submission : 17/May/2004)
(Second Notification to authors : 7/June/2004)
(Deadline for Camera Ready Papers : 01/July/2004)
(Publication of the special issue : end of August/2004)
All submissions of the abstract and papers in latex and ps formats
should be sent to the guest editors via email
([email protected]). For further information about the
special issue, please do not hesitate to contact the guest editors via
Takashi Washio Email: [email protected] Address:
Institute for Scientific and Industrial Reseach, Osaka University 1-8,
Mihogaoka, Ibarakishi, Osaka, 567-0047, Japan
For details about the policy of the FUNDAMENTA INFORMATICAE journal
and the requirements for prospective authors, see a recent issue of
the journal or check the journal's web site http://fi.mimuw.edu.pl/.
------------------------------
From: "Sarabjot Singh Anand" <[email protected]>
Subject: AAAI Workshop on Semantic Web Personalization
Date: Tue, 27 Jan 2004 09:48:53 -0000
CALL FOR PAPERS
AAAI 2004 Workshop on Semantic Web Personalization=20
http://maya.cs.depaul.edu/~mobasher/swp04/
July 25-26, 2004, San Jose, California
IMPORTANT DATES
March 12, 2004: Deadline for electronic submission
April 16, 2004: Notification of acceptance or rejection
May 14, 2004: Submission of camera-ready paper via AAAI Web site
DESCRIPTION OF THE WORKSHOP
The Web is now an integral part of numerous applications in which a
user interacts with a company, government, employer, or an information
provider. However, the potential of the Web is hampered by the
enormity of the content available and the diverse expectations of its
user base. Hence, Web applications need to combine all available
knowledge in order to form personalized, user-friendly, and
business-optimal services.
Over the years, personalized Web applications and services have been
developed that use Web Mining and similar technologies to harvest
shallow patterns hidden within masses of transactional, navigational,
and content-structural data that are useful for presenting product
recommendations and the likes. Without the benefit of deeper semantic
or ontological knowledge about the underlying domain, personalization
systems cannot handle heterogeneous and complex objects based on their
properties and relationships. Nor can these systems possess the
ability to automatically explain or reason about the user models or
user recommendations. This realization points to an important research
focus that combines the strengths of Web mining with semantic or
ontological knowledge. The prospect of having deeper knowledge, gained
from a combination of relevant but highly heterogeneous sources, about
the information available and/or the resources accessed by users,
means that personalization approaches can be developed that can
present the most contextually relevant content to the user of the Web.
The workshop aims to bring together researchers and practitioners from
the two rapidly developing research areas: Semantic Web and Web
Intelligence. The aim is to improve the results of Web Personalization
by exploiting the new semantic structures in the Web, and by
incorporating AI techniques that take advantage of existing, learned,
or extracted ontological knowledge.
TOPICS OF INTEREST
We invite submissions covering the full range of topics related to
Semantic Web Personalization, from foundational issues of obtaining,
modelling, and integrating relevant data, to the deployment and
evaluation of these techniques in concrete architectures and
systems. We also encourage methodological contributions covering new
developments in the basic enabling technologies with a specific view
to the demands of Semantic Web Personalization. Topics of interest
include (but are not limited to):
Data/Knowledge Modeling, Integration and Management
o The role of domain knowledge and ontologies in user modeling and
personalization o Combining background knowledge and user context
o Semantic Web Mining using the syntactic layer (XML), the vocabulary
layer (e.g., RDF-Schema), or the logical layer (e.g., Description
Logics/OIL)
o Integration of content, structure and usage data for personalization
o The role of multi-channel data in online personalization
o Personalized taxonomies or ontologies (for individuals or user
communities)
o Model integration for personalization and recommendation systems
Architectures and Systems
o Semantically enhanced scalable collaborative filtering techniques
o Ontology-based agents for intelligent information access and
filtering
o Adaptive systems for the Semantic Web
o Hybrid Recommendation Systems
o Multi-agent systems for personalization, including client-side or
distributed architectures
o Community-based and task-oriented personalization
o Evaluation of Recommendation Systems
Enabling Technologies for Personalization
o Web usage, content, and structure mining
o Text and hypertext mining for recommendation generation and
personalization
o Automated techniques for generation and updating of user profiles
o Machine Learning techniques for information extraction and
integration
o Learning and acquisition of taxonomies or ontologies from Web
resources
o Metadata learning and Harvesting=20
o Applications of relational data mining in personalization
PAPER SUBMISSION
All papers must be submitted no later than March 12, 2004. All
submissions must be made electronically to [email protected].
Please use the AAAI prescribed formatting instructions available at
http://www.aaai.org/Workshops. Papers should be no more than 12 pages
inclusive of all references and figures. All papers must be submitted
in either PDF (preferred) or postscript. It is the responsibility of
the authors to ensure that the submitted papers print correctly on a
variety of printers. If any special fonts are used, they must be
included in the submission. All papers must be original, and have not
been published or submitted elsewhere.
For more information, visit http://maya.cs.depaul.edu/~mobasher/swp04/
------------------------------
From: Patrick Doherty <[email protected]>
Subject: 4th International Cognitive Robotics Workshop
Date: Tue, 27 Jan 2004 12:25:05 +0200
First Call for Papers
The 4th International Cognitive Robotics Workshop
http://www.ida.liu.se/~patdo/cogrob04/
Co-Located with ECAI 2004
August 23 and 24, 2004
Valencia, Spain
Workshop Description
Research in robotics has traditionally emphasized low-level sensing
and control tasks including sensory processing, path planning, and
manipulator design and control. In contrast, research in cognitive
robotics is concerned with endowing robots and software agents with
higher level cognitive functions that enable them to reason, act and
perceive in changing, incompletely known, and unpredictable
environments.
Such robots must, for example, be able to reason about goals, actions,
when to perceive and what to look for, the cognitive states of other
agents, time, collaborative task execution, etc. In short, cognitive
robotics is concerned with integrating reasoning, perception and
action with a uniform theoretical and implementation framework.
Combining results from the traditional robotics discipline with those
from AI and cognitive science has and will continue to be central to
research in cognitive robotics.
This workshop aims to bring together researchers involved in all
aspects of the theory and implementation of cognitive robotics, to
discuss current work and future directions. While all aspects of
cognitive robotics are of interest to the workshop, we especially
welcome discussions and demonstrations of implemented systems.
Submission Information
Potential participants are invited to submit either
- a technical paper (extended abstract)
- an overview on their ongoing research,
- a position paper,
- a statement of interest,
- or a description of an implemented system that the authors are
willing to demonstrate at the workshop.
For the sake of uniformity, all technical papers should follow the
ECAI 2004 style guide and should be no longer than 5 pages in camera
ready PDF format. Author names should be included. Please refer to the
ECAI submission process for details. (See workshop homepage).
Others wishing to attend should submit a 1-2 page description of their
work or interest in this area (including a short list of related
publications). This may include specific questions and issues that
they feel should be addressed. Proposals of panels on specific issues
are also welcome.
Authors who would like to participate in systems demonstrations
(either live, simulated, or video-taped) should indicate their
audio-visual and/or computer needs at the time of submission.
If the quality of the submissions is sufficiently high, we may look
into the possibility of publishing extended versions of selected
articles in a special journal issue.
All submissions must arrive by May 10, 2004. Only electronic
submissions will be accepted and all papers must be in PDF format.
All submissions should be sent to [email protected]
Important Dates
Submission Deadline: May 10, 2004
Notification of Acceptance: May 26, 2004
Submission of camera ready copies: June 6, 2004
For more information, visit http://www.ida.liu.se/~patdo/cogrob04/
------------------------------
From: "IEEE/WIC/ACM WI/IAT Conference Secretariat" <[email protected]>
Subject: Learning and Self-Adapting Agents (IEEE/WIC/ACM WI-IAT'04)
Date: Tue, 27 Jan 2004 17:08:13 +0900
Call for Workshop Proposals: Learning and Self-Adapting Agents
http://www.maebashi-it.org/WI04/workshop.php
(In conjunction with the 2004 IEEE/WIC/ACM International Joint
Conference on Web Intelligence (WI'04 http://www.maebashi-it.org/WI04/)
and Intelligent Agent Technology (IAT'04 http://www.maebashi-it.org/IAT04/)
Workshops will be held at the beginning of the conference,
September 20, 2004 at King Wing Hot Spring Hotel, Beijing, China.
The 2004 IEEE/WIC/ACM WI/IAT Conference Secretariat
[email protected]
The 2004 IEEE/WIC/ACM Web Intelligence (WI'04)
http://www.maebashi-it.org/WI04/
http://www.comp.hkbu.edu.hk/WI04/
The 2004 IEEE/WIC/ACM Intelligent Agent Technology (IAT'04)
http://www.maebashi-it.org/IAT04/
http://www.comp.hkbu.edu.hk/IAT04/
------------------------------
From: Eugene Eberbach <[email protected]>
Subject: CEC 2004: Application of Cultural Algorithms in Industry and Engineering
Date: Tue, 27 Jan 2004 05:25:17 -0500
CEC 2004 Special Session Announcement
Applications of Cultural Algorithms in Industry and Engineering
Robert Reynolds
More information at: http://www.cs.unr.edu/~sushil/cec/#ACAIE
This special session will focus on applications of Cultural
Algorithms, a type of evolutionary learning based upon cultural
evolution, to problems in industry and engineering. Example
applications include approaches to assembly line balancing,
alternative fuel vehicles, consumer response to automobile price
incentives, engineering design, among others.
We solicit papers addressing these and related topics.
Robert Reynolds
Department of Computer Science
5143 Cass Avenue
424 State Hall
Wayne State University
Detroit, MI 48202
Tel: 313-577-0726
Fax: 313-577-6868
------------------------------
From: Eugene Eberbach <[email protected]>
Subject: CEC 2004: Learning by Estimating Distributions in Evolutionary Computation
Date: Mon, 26 Jan 2004 06:12:03 -0500
CEC 2004 Special Session Announcement
Learning by Estimating Distributions in Evolutionary Computation
Nikolaus Hansen, Stefan Kern, Jiri Ocenasek, and Petros Koumoutsakos
More information at: http://www.cs.unr.edu/~sushil/cec/#LEDEC
Continuous Evolutionary Algorithms use probability distributions in
their variation operators to sample new search points
(offspring). Usually, no particular knowledge of a suitable choice of
the parameters or even the type of the probability distribution for an
optimization problem is available. For this reason, reliable and
efficient strategies are needed to learn probability distributions,
based on the information provided by the selection of promising
offspring.
The idea of introducing learning to evolutionary algorithms to enhance
their efficiency is not new: In evolution strategies, this form of
learning is usually referred to as 'adaptation'. In genetic
algorithms, the learning is called 'estimation of distribution' or
'learning probability distributions'.
For this special session, we want to bring together leading researchers
and practitioners from these areas.
Please send correspondence to Nikolaus Hansen
Institute of Computational Science / Computational Lab,
Swiss Federal Institute of Technology Zuerich,
ETH Zentrum, HRS H3,
CH-8092 Zuerich, Switzerland.
Phone: +41 1 632 0638
Fax: +41 1 632 1703
------------------------------
From: Eugene Eberbach <[email protected]>
Subject: CEC 2004: Evolutionary Scheduling
Date: Mon, 26 Jan 2004 06:09:41 -0500
CEC 2004 Special Session Announcement
Evolutionary Scheduling
Dr. Edmund Burke, Dr. Kay Chen Tan, and Dr. G. Kendall
More information at: http://www.cs.unr.edu/~sushil/cec/#ES
The session will cover all aspects of evolutionary scheduling and
related issues. We would hope to attract a balance of applied and
theoretical papers from across the evolutionary computing and
meta-heuristic research communities. Typical examples of such problems
include rostering, machine scheduling, timetabling, vehicle routing,
resource assignment, planning, etc. This special track invites
submissions in all areas of evolutionary scheduling and
metaheuristics.
Dr. Edmund Burke
Automated Scheduling, Optimisation and Planning Research Group
School of Computer Science and Information Technology
University of Nottingham
NOTTINGHAM NG8 2BB, UK.
e-mail: [email protected]
Tel: +44 (0)115 951 4206
Fax: +44 (0)115 951 4249
WWW: http://www.cs.nott.ac.uk/Department/Staff/ekb/
Dr. Kay Chen Tan
Department of Electrical and Computer Engineering National University of
Singapore
4 Engineering Drive 3, Singapore 117576,
Republic of Singapore
Tel: (65) 6874 2127
Fax: (65) 6779 1103
http://vlab.ee.nus.edu.sg/~kctan WWW: http://vlab.ee.nus.edu.sg/~kctan
Dr. G. Kendall
Automated Scheduling, Optimisation and Planning Research Group
School of Computer Science and Information Technology
University of Nottingham
NOTTINGHAM NG8 2BB, UK.
e-mail: [email protected]
Tel: +44 (0)115 951 4206
Fax: +44 (0)115 951 4249
WWW: http://www.cs.nott.ac.uk/~gxk/
------------------------------
From: Eugene Eberbach <[email protected]>
Subject: CEC 2004: Evolutionary Computing in the Process Industry
Date: Tue, 27 Jan 2004 05:29:11 -0500
CEC 2004 Special Session Announcement
Evolutionary Computing in the Process Industry
Rajkumar Roy and Ashutosh Tiwari
More information at: http://www.cs.unr.edu/~sushil/cec/#ECPI
Submission deadline: February 7, 2004
There is an ever-increasing demand in the process industry to become
more flexible, more responsive and to be competitive with energy
efficiency. The competition is fierce; complex products are required
at higher quality at the same cost si nce margins are continuously
being squeezed. In order to succeed in such competitive environment,
the industry seeks innovative intelligent systems to enhance its new
product and process development strategies.
Traditional methods often employed to solve complex optimisation
problems in the process industry tend to inhibit elaborate exploration
of the search space, often resulting in sub-optimal
solutions. Evolutionary Computation (EC) is generating considerable
interest for solving these problems. It is proving robust in
delivering global optimal solutions and helps to resolve limitations
encountered in traditional methods. EC harnesses the power of natural
selection to turn computers into optimisation tools. Most industrial
processes (e.g. in metal forming industry, chemical industry, paper
industry, etc.) are large scale, high dimensional, non-linear and
uncertain with highly skilled operators to control the process
plants. While many issues have been addressed in recent research
efforts, limitations for wider applications of these techniques to
process industry still exist that restrict more realistic solutions to
be achieved. Current challenges include, for example, complexity of
the search space, nature of constraints, multiple objectives, and
search within integrated qualitative/quantitative space.
This special track invites submissions in all areas of evolutionary
computation dealing with the challenges of applying EC techniques to
real world problems in the process industry.
Rajkumar Roy and Ashutosh Tiwari
Enterprise Integration
School of Industrial and Manufacturing Science (SIMS)
Cranfield University, Cranfield
Bedfordshire, MK43 OAL, UK
Tel: +44 (0) 1234 754936
Fax: +44 (0) 1234 750852
Email: {r.roy,a.tiwari}@cranfield.ac.uk
------------------------------
From: Eugene Eberbach <[email protected]>
Subject: CEC 2004: Recent Developments in Artificial
Date: Wed, 28 Jan 2004 05:27:03 -0500
CEC 2004 Special Session Announcement
Recent Developments in Artificial Immune Systems
Jonathan Timmis and Dr. Leandro N. de Castro
More information at: http://www.cs.unr.edu/~sushil/cec/#AIS
The mammalian immune system is a remarkably complex interacting
network of cells that at a basic level, protects hosts from
infections. There are many difficulties facing the immune system, such
as the vast array of stimuli that can infect the host, the continual
bombardment of such stimuli (there is no resting for the immune
system) and the countless interactions that occur with other processes
and systems within the host (such as the neural systems and endocrine
or hormonal systems). The remarkable ability if the immune system to
react to these stimuli (antigens) and remove the majority of them from
our system has fascinated researchers over the years. More light is
being shed day by day through work by immunologists, and these
findings have caught the attention of computer scientists. The reason
for this is that the immune system has many properties that are very
desirable for use in computer systems: recognition of stimuli,
learning about new stimuli, remembering past infections, communication
mechanisms, robustness of the system and the distributed nature of the
immune system. All of these are properties have been inspiring
computer scientists for the past decade to build systems that mimic in
some way these properties of the immune system, this area of research
is known as Artificial Immune Systems (AIS).
Within AIS, there is no one standard AIS algorithm, however, there are
a number of basic flavours of AIS algorithms that draw their
inspiration from certain processes within the immune system. To date
there are clonal selection, immune network, bone marrow and negative
selection algorithms. There are many variations on these algorithms,
but there is at least some basic acceptance, for example, of what a
clonal selection algorithm consists of and how it should work.
These basic algorithms then form the foundation for the plethora of
other algorithms that are applied in a vast array of application
areas. These range from optimisation, to machine learning, to data
mining, to software testing, to fault tolerance, to computer security,
to virus detection and the list goes on.
This session will aim highlight the latest in the developments of
artificial immune systems, in terms of algorithm development,
application and theoretical analysis. Papers are invited for
submission on unpublished work in the following (but not restricted
to) areas:
* AIS algorithm developments
* New paradigms in AIS such as danger theory
* Theoretical studies in AIS
* Applications of AIS
* Modelling of immune system components and processes
* Frameworks for AIS development
Dr. Jonathan Timmis
Computing Laboratory
University of Kent
Canterbury, Kent. CT2 7NF
WWW: http://www.cs.kent.ac.uk/~jt6/
Tel: +44 (0) 1227 823636
Dr. Leandro N. de Castro
Catholic University of Santos
Brazil
http://www.dca.fee.unicamp.br/~lnunes
------------------------------
From: Eugene Eberbach <[email protected]>
Subject: CEC 2004: EC in the Optimisation of Semiconductor Manufacturing and Testing
Date: Wed, 28 Jan 2004 05:29:21 -0500
CEC 2004 Special Session Announcement
EC in the Optimisation of Semiconductor Manufacturing and Testing
More information at: http://www.cs.unr.edu/~sushil/cec/#ECOSMT
This special session invites original contributions using evolutionary
computation techniques in the optimisation of semiconductor industry
applications.
Automated analysis for semiconductor wafer defect data has become
increasingly important over the past several years as a means of
quickly understanding and controlling contamination sources and
process faults which impact product yield. Larger semiconductor wafer
and smaller defect size have caused an exponential increase in the
volume of visual and parametric defect data that must be analysed,
evaluated and maintained. The ability of a manufacturer to readily
access this data and to quickly extract useful process knowledge is
required as market trends cycle drive the cycle time down.
There is therefore the need to develop automated intelligent analysis
and reduction algorithms that correlate facility, design, process,
test and work-in-process data. Methods such as automatic defect
classification, spatial signature analysis, statistical process
control, and Data Mining are but a few of the technologies being
developed and tested in the fabrication environment today as a means
of adding informational content to the raw measured data.
------------------------------
From: "Baowen Xu" <[email protected]>
Subject: WCCW2004 Call for Papers: First International Workshop on Web
Computing in Cyberworlds
Date: Tue, 27 Jan 2004 18:04:52 +0800
WCCW2004 Call for Papers
First International Workshop on Web Computing in Cyberworlds (WCCW2004)
at the International Conference on Cyberworlds 2004
Tokyo, November 18-20, 2004
http://cse.seu.edu.cn/people/bwxu/wccw2004
Aims
The open approach to developing Web computing in Cyberworlds has
attracted an increasing attention in both academia and industry. This
workshop will not only focus on architecture and models for Web
computing, but also emphasize the emerging technologies in various Web
computing aspects, which will be held together with the International
Conference on Cyberworlds 2004 (http://cw2004.myvnc.com/).
The Web Computing is an ideal model to utilize the millions of
personal computers?? idle CPUs through the Web, thus providing high
efficient and cheap computation. The distributed and dynamic
architecture and system models have become the foundation of Web
Computing. The inherent cooperation in Web computing enables a large
range of computations.
Aims The aim of this workshop is to bring together researchers and
practitioners working on theory, techniques and applications,
concerning analysis and/or manipulation of Web computing. The complex
and large-scale Web computing requires effective methodologies and
tools for the analysis, design, implementation and maintenance.
Topics
The workshop emphasizes on the analysis and manipulation techniques.
Topics include, but not limited to:
Architecture and Models
- Web Computing Model and Framework
- Web Computing Software Environment
- Heterogeneity and Portability in Web Computing
- Semantics and Ontology Engineering
Methods and Tools
- Web Computing and Distributed Technologies
- Security and Accessibility in Web Computing
- Proxy and Cache Techniques
- Neural Networks, Fuzzy Logic, Rough Sets, and Evolutionary Computation
Applications
- Applications of Web Computing
- Web Information Filtering and Retrieval
- Clustering-Based Recommended Systems
- Web-Based Applications and Systems
Quality Assurance
- Cooperation and Integration
- Testing and evolution
- Maintenances of Web Computing Systems
Submission
Original papers on new results in the rapidly emerging area ?C web
computing in Cyberworlds are welcome. Papers should indicate the
innovative aspects of the results and contribution to the
field. Papers submitted
For publication in a journal or another conference will not be
considered. All submitted papers will be evaluated according to its
originality, significance, correctness, presentation and
relevance. Papers must be submitted electronically in Postscript or
PDF format via E-mail to professor Baowen Xu ([email protected]). The
total number of the accepted papers will be no more than 20.
Papers should conform to the IEEE paper guidelines:
http://www.computer.org/cspress/instruct.htm
Accepted papers will published in the proceedings of Cyberworlds 2004
and will be published by IEEE Computer Society Press.
Important Dates
Paper submissions due: 1st May 2004
------------------------------
From: Jon Smid <[email protected]>
Subject: PSMP3 Workshop: Knowledge Representation and Acquisition for Knowledge Presentation, Sharing, Mining and Protection
Date: Thu, 29 Jan 2004 02:12:53 -0500 (EST)
C A L L F O R P A P E R S
The P S M P 3 Workshop
featuring
KNOWLEDGE REPRESENTATION and ACQUISITION for
Knowledge Presentation, Sharing, Mining and Protection
in CYBER COMMUNITIES.
http://jewel.morgan.edu/~jsmid/psmp3/
June 21 - 24, 2004
Monte Carlo Resort, Las Vegas, Nevada, USA
The PSMP3 workshop is a continuation of the first PSMP workshop, Las
Vegas, June 2003 and of the second PSMP2 workshop, Innsbruck, Austria,
February 2004. The PSMP 3 workshop is organized within The 2004
International Multiconference in Computer Science and Computer
Engineering.
PSMP 3 WORKSHOP TOPICS
The primary focus of the PSMP3 workshop is knowledge representation
and knowledge acquisition. The following topics are suggested as
particular examples of interest to the workshop. Submissions are not
limited to these topics.
o Ontologies, knowledge representations, e.g. semantic nets,
property-based representation, semantic types.
o Semantics theories
o Knowledge acquisition via semantic mappings
o Syntax and semantics applications
o Wordnet, Semantic Web approaches
o Applications:
o Tutorial and dialog systems in cyber communities
o Inference in dialog and language acquisition systems, current
status of dialog systems and their limitations
o Interaction in networks
o Sub-natural language interface problems
o Dialogs in peer-to-peer networks
o Dialogs for robot communities
o Dialogs in agent communities
o Machine versus human readable WWW
o Abstract models of the above topics
PROCEEDINGS
The PSMP 3 workshop papers will be published in the proceedings of
The 2004 International Multiconference in Computer Science and
Computer Engineering. The conference proceedings will be published
by CSREA Press (ISBN) in hardcopy. It will be a multivolume
set. The proceedings will be available at the conference. Some
accepted papers will also be considered for journal publication
(soon after the conference). All conference proceedings published
by CSREA Press are considered for inclusion in major database
indexes that are designed to provide easy access to the current
literature of the sciences (database examples: ISI Thomson
Scientific, IEE INSPEC, DBLP, ...).
SUBMISSION OF CONTRIBUTIONS
Please send proposals to J.Smid at [email protected].
Prospective authors are invited to submit via email draft papers
(about 5 pages - single space, font size of 10 to 12) by the due
date. The length of the Camera-Ready papers (if accepted) will be
limited to 7 (IEEE style) pages. Papers must not have been
previously published or currently submitted for publication
elsewhere. The first page of the draft paper should include: Title
of the paper, Name, Affiliation, postal address, E-mail address,
telephone number, and fax number for each author. The first page
should also include the name of the author who will be presenting
the paper and a maximum of 5 keywords.
IMPORTANT DATES:
February 16, 2004: Draft papers due
March 22, 2004: Notification of acceptance
April 21, 2004: Camera-Ready papers & Prereg. due
June 21-24, 2004: The PSMP3 Workshop, The 2004 MultiConference
Please refer to http://jewel.morgan.edu/~jsmid/psmp3/ for further details.
------------------------------
From: [email protected]
Subject: First Workshop ROC Analysis in AI
Date: Thu, 29 Jan 2004 14:14:01 +0100
Call for Papers
First Workshop on ROC Analysis in AI, ROCAI2004
http://www.dsic.upv.es/~flip/ROCAI2004/
Valencia, Spain, 22-23 August, 2004
Submission Deadline: 15 April, 2004.
to be held within ECAI2004, http://www.dsic.upv.es/ecai2004/
the European Conference on Artificial Intelligence
Overview
Receiver Operating Characteristic Analysis (ROC Analysis) is related
in a direct and natural way to cost/benefit analysis of diagnostic
decision making. Widely used in medicine for many decades, it has been
introduced relatively recently in some areas of artificial
intelligence: machine learning, multiagent systems, intelligent
decision support and expert systems. In this context, ROC analysis
provides tools to select possibly optimal models and to discard
suboptimal ones independently from (and prior to specifying) the cost
context or the class distribution. Furthermore, the Area Under the ROC
Curve (AUC) has been shown to be a better evaluation measure than
accuracy in contexts with variable misclassification costs and/or
imbalanced datasets. AUC is also the standard measure when using
classifiers to rank examples, and, hence, is used in applications
where ranking is crucial, such as campaign design, model combination,
collaboration strategies, and co-learning.
Nevertheless, there are many open questions and some limitations that
hamper a broader use and applicability of ROC analysis. Its
connections with other evaluation measures is not yet clarified
completely, its incorporation in decision support and expert systems
technology just envisaged, its use for improving the decisions of
(communities of) intelligent agents unexplored, and its use in data
mining still below its full potential. Among the limitations of ROC
analysis, an important one, despite some recent progress, is its
possible but difficult extension for more than two classes.
One of the main goals of the workshop is to foster the
cross-fertilisation of ideas and applications with related areas in
artificial intelligence. Consequently, the presentations and
discussions will be open to a broad list of topics (not exhaustive):
* Adaptation of classical learning methods for improving AUC instead
of accuracy.
* Agent selection/ranking in multiagent systems.
* Alternative ROC representations.
* Alternatives to AUC measures (such as AUC*).
* Analysis of the performance of learners or decision systems based
on AUC.
* Applications of ROC Analysis in Expert Systems.
* Classifier Evaluation.
* Co-learning (collaborative learning) and ROC Analysis.
* Consensus and Collaborative/Distributed Decision Making.
* Constraint Satisfaction Methods for ROC Analysis.
* Cost-sensitive Learning.
* Decision Networks and Probabilistic Reasoning with ROC Analysis.
* Expert Systems, Knowledge Bases and ROC Analysis.
* Inductive Logic Programming and ROC Analysis.
* Multi-class ROC on top of binary ROC.
* Oversampling and ROC analysis.
* Precision & Recall measures in Information Retrieval.
* Ranking Actions. Applications in Planning and Robotics with
variable contexts.
* Reinforcement Learning and ROC analysis.
* ROC Analysis for Model Building and Modification.
* ROC Analysis for Descriptive Data Mining (association rules,
subgroup discovery).
* Soft classifiers and Probability Estimators.
* Software Packages and Efficient Implementations (Convex Hull).
* Use of ROC analysis and measures as fitness and selection
criteria in evolutionary techniques.
* Working with Imbalanced datasets.
Details of the workshop
This is a one-day workshop, with sessions consisting of short paper
presentations, devoting an important share of time to informal
discussion and interaction between the participants. The workshop
will be closed with an open discussion about more promising open
problems and research areas of ROC analysis, continuation of the
workshop, future related events, etc.
Papers will be selected by the program committee according to the
quality of the submission and its relevance to the workshop
topics. All accepted papers will be gathered in printed form and
distributed to registered attendees as workshop notes. The
publication of a selected set of papers for a special volume or a
journal issue is considered, but this will depend on the success and
overall results of the workshop.
Important dates
* Call for papers: 20 January 2004
* Deadline for the workshop papers: 15 April 2004
* Notification of acceptance: 15 May 2004
* Camera Ready copies: 1 June 2004
* Workshop dates: 22 or 23 August 2004 (soon to be determined,
depending on the ECAI organising committee)
Submission Guidelines
Potential participants are invited to submit short papers (no longer
than 10 pages), which may be in the form of a technical paper, a
position paper (e.g. highlighting open problems or new applications of
ROC analysis), an overview of their research or a software
demonstration.
Authors should submit their papers electronically (PDF or PS format)
to the contact person ([email protected]). It is recommended to
submit papers using the final camera-ready ECAI 2004 conference paper
style (http://www.dsic.upv.es/ecai2004/cfp/style/style.html) including
author names.
Those wishing to attend the meeting without submitting a paper should
send a short statement of interest to the contact person describing
their work or interest in the area.
For more information, visit http://www.dsic.upv.es/~flip/ROCAI2004/
------------------------------
From: "Ina Lauth" <[email protected]>
Subject: KDNet Symposium on Knowledge-Based Services for the Public Sector
Date: Fri, 30 Jan 2004 18:59:52 +0100
Call for Papers
KDNet Symposium on Knowledge-Based Services for the Public Sector
Bonn, Germany, June 3-4, 2004 http://symposium.kdnet.org/
KDNet, the European Knowledge Discovery Network of Excellence, is
organizing a symposium to present Knowledge Discovery (KD) research
projects and applications aimed at information management in the
public sector. The symposium is structured in a number of workshops
concerning different aspects of KD in the public sector. Currently,
three workshops and an exposition for the demos are
scheduled. Workshops are:
1. KNOWLEDGE DISCOVERY IN THE ENVIRONMENTAL DOMAIN
2. MINING OFFICIAL DATA
3. KNOWLEDGE-BASED SYSTEMS AND SERVICES FOR HEALTH CARE
The symposium will maintain a balance between theoretical issues and
descriptions of case studies to promote synergy between theory and
practice. Therefore, the target group is that of researchers and
applicants of KD tools from the academia, research institutions,
government organisations and industry. The meeting will allow
participants to learn about the many different applications of KD in
the public sector.
Paper submission
Research work presenting theoretical results, basic and applied
research, perspective solutions and practical developments are
welcome, provided they address the topic of one of the workshops. For
more information on workshop topics please refer to the home page of
workshops available at http://symposium.kdnet.org/ Papers should be
original and not previously published elsewhere. Position papers (4
page abstracts) of current projects including new solution ideas and
visions statements are also welcome.
Submissions must refer to one of the three workshops and should comply
submission procedures indicated for each workshop. All submissions
will be reviewed by the respective program
committees. Extended/revised versions of selected papers will be
considered for inclusion in an edited book
Important dates
- Submission deadline: Monday March 15, 2004
- Notification of acceptance: Thursday April 15, 2004
- Early registration: Saturday May 1, 2004
- Camera-ready copies due: Wednesday May 5, 2004
- Workshops: Monday June 3 through Tuesday June 4, 2004
Grants
A number of grants will be available in order to help students to take
part in the symposium. Priority will be given to authors of accepted
papers. Proof of student status will be required.
For more information, visit http://symposium.kdnet.org/
------------------------------
From: Thomas Zeugmann <[email protected]>
Subject: Algorithmic Learning Theory 2004; Discovery Science 2004
Date: Sat, 31 Jan 2004 00:02:21 +0100 (MET)
Call for Papers: ALT 2004
The 15th International Conference on Algorithmic Learning Theory
http://www.tcs.uni-luebeck.de/pages/thomas/ALT04/alt04.jhtml
University of Padova, Padova, Italy, October 2-5, 2004
and
Call for Papers: DS 2004
The 7th International Conference on Discovery Science
http://www.slab.dnj.ynu.ac.jp/DS04/
University of Padova, Padova, Italy, October 2-5, 2004
The 15th International Conference on Algorithmic Learning Theory (ALT
2004) and the 7th International Conference on Discovery Science will
be held at the University of Padova, Padova, Italy, October 2-5, 2004
are part of the Padova Dialogues 2004
http://thepadovadialogues.dei.unipd.it/
The SUBMISSION DEADLINE for all conferences is MAY 22, 2004.
For any further information, please visit the web-sites given above.
------------------------------
From: "Roy, Rajkumar" <[email protected]>
Subject: Evolutionary Computation in Industry (ECI-2004) track at GECCO-2004
Date: Sun, 1 Feb 2004 18:15:36 -0000
EVOLUTIONARY COMPUTATION IN INDUSTRY (ECI-2004)
part of the Genetic and Evolutionary Computation Conference (GECCO)
Seattle, Washington USA June 26-30, 2004 (Saturday - Wednesday)
http://www.isgec.org/gecco-2004/
For the third year, GECCO in 2004 will have a series of sessions
entitled "Evolutionary Computation in Industry". The Evolutionary
Computation in Industry sessions are tutorial-style and presenters are
invited, but all GECCO participants are invited to attend. The ECI
sessions will be scheduled later, but are expected to be on June 28-30
(Monday - Wednesday) during the main part of GECCO conference.
Each session focuses on a different topic related to applications of
evolutionary algorithms. The presentations are designed for attendees
such as managers, technology scouts, and industrial practitioners, who
are seeking less technical presentations on the ways that evolutionary
applications can make a difference. Presenters in these sessions will
be experts in applications and in describing the way that good
evolutionary computation projects are planned and executed. Sample
topics in the sessions include project case histories, descriptions of
successful projects, and project descriptions organized around topics
such as chemical applications, governmental applications, and
applications in the area of industrial design.
The Evolutionary Computation in Industry sessions are organized this
year by
--- David Davis (NuTech Solutions) [[email protected]]
--- Rajkumar Roy (Cranfield University) [[email protected]]
--- Mark Jakiela (Washington University in St. Louis) [[email protected]]
------------------------------
From: Maarten <[email protected]>
Subject: Late Breaking Papers at GECCO 2004
Date: Mon, 2 Feb 2004 10:40:04 +0100
CALL FOR GECCO-2004 LATE-BREAKING PAPERS
Late-Breaking Paper Deadline: May 21, 2004
Genetic and Evolutionary Computation COnference (GECCO-2004)
June 26-30, 2004 (Saturday-Wednesday)
Red Lion Hotel
Seattle, Washington, USA
A recombination of the
13th International Conference on Genetic Algorithms (ICGA) and
the 9th Genetic Programming Conference (GP)
http://www.isgec.org/gecco-2004/
Papers describing late-breaking developments in the field of genetic
and evolutionary computation are being solicited for presentation at
the Genetic and Evolutionary Computation 2004 Conference (GECCO-2004)
to be held on June 26-30 (Saturday-Wednesday), 2004 at the Red Lion
hotel in Seattle, Washington USA, and inclusion in a special CD-ROM to
be distributed to all attendees of the conference. This special CD-ROM
is distinct from the conference proceedings.
Late-breaking papers will be briefly examined for relevance and
minimum standards of acceptability, but will not be peer reviewed in
detail. Paper acceptance decisions will be made as soon as possible
after receipt of the submission, so late-breaking papers may be
submitted any time between now and the May 21, 2004 deadline.
Note that all papers included in the Late Breaking Papers CD-ROM must
also be presented at GECCO-2004. At least one author of each Late
Breaking Paper must register for GECCO-2004, or the paper will not
appear in the Late Breaking Papers CD-ROM.
We currently plan that late-breaking papers will be presented orally
in special sessions held during GECCO-2004.
Authors will individually retain copyright (and all other rights) to
their late-breaking papers and should feel free to submit them (either
before or after the above deadline) for publication by other
conferences or journals.
SUBMISSION PROCEDURE
Late Breaking Papers must be RECEIVED in electronic (PDF) camera-ready
format no later than 21 May 2004. Late-breaking papers must be
submitted in camera-ready form in accordance with the camera-ready
GECCO- 2004 format specifications that can be found at the GECCO-2004
web site. Late-breaking papers should be no more than TWELVE (12)
pages in length.
To submit please: All 4 of the following items must be submitted by
May 21, 2004. Because the late-breaking papers are published on a
very tight time schedule, please be very attentive in carrying out
each of the following 4 steps correctly no later than May 21, 2004:
(1) Send a PDF electronic copy of your paper as an email attachment to
the LBP chair, Maarten Keijzer (email:
[email protected]). Late-breaking papers must be submitted in
camera-ready form in accordance with the camera-ready GECCO-2004
format specifications that can be found at the GECCO-2004 web
site. Late-breaking papers should be no more than 12 pages in length.
Please be very careful about formatting your paper (and testing it, by
printing it out) because of the very tight time schedule. No
paper-based submissions can be accepted.
(2) FAX a SIGNED "permission to publish" form (that can be downloaded
from the GECCO-2004 web site) to the American Association for
Artificial Intelligence (FAX: +1-650-321-4457). No paper-based
submissions can be accepted.
(3) Send a plain text email to both [email protected] and
[email protected] including the following information:
--- First Name, Last Name, and e-mail for all the authors of the paper
--- Paper title
--- Abstract
--- Name of the proposed presenter of the paper
(4) At least one presenter of the paper must have paid the
registration fee and be registered for GECCO-2004 by May 21,
2004. Registration may be accomplished in several ways (including FAX
and credit card).
Since there will be no opportunity for revisions, authors should be
especially careful that their original submission is fully compliant
with all requirements above.
PRODUCING A PDF VERSION OF YOUR MANUSCRIPT
PDF documents can be produced either by using commercial software
available from Adobe or by using free conversion tools for Windows or
the ps2pdf and pdflatex utilities under Unix/Linux (with links at the
GECCO-2004 web site). In addition, recent versions of MS Word may be
able to save directly in PDF format. Please, preview your PDF file
with acrobat reader to check that all the fonts and figures are
properly reproduced before submitting the manuscript.
For more information, visit http://www.isgec.org/gecco-2004/
------------------------------
From: Dave Andre <[email protected]>
Subject: ICML competition and workshop on Physiological Data Modeling
Date: Mon, 2 Feb 2004 14:34:33 -0500
ICML 2004 workshop
The Physiological Data Modeling Contest (PDMC)
A Machine Learning Challenge
July 8th, 2004
Banff, Alberta, Canada
http://www.cs.utexas.edu/users/sherstov/pdmc
Physiological data offers many challenges to the machine learning
community including dealing with large amounts of data, sequential
data, issues of sensor fusion, and a rich domain complete with noise,
hidden variables, and significant effects of context.
The Physiological Data Modeling Contest (PDMC) will challenge
participants to exhibit machine learning algorithms for classification
and regression on data taken using BodyMedia (www.bodymedia.com)
wearable body monitors. These devices collect and store continuous
data from multiple sensors packaged in an unobtrusive armband.
To enable this contest, BodyMedia is providing a rich dataset
comprising several months of data from more than two dozen
subjects. Features include raw data such as skin temperature, heat
flux, galvanic skin response, and vital statistics of the user. The
tasks include detecting classes of activity being engaged in by the
user (e.g. walking, sleeping, watching TV, etc.) based on the values
of these features. The training data is available now; the test data
will be released approximately four weeks before the workshop; and the
competitors will submit entries consisting of predictions for this
test data shortly before ICML 2004.
At the workshop, the performance of each entrant will be announced and
the various techniques discussed and analyzed in detail. A small prize
will be awarded to the winning competitors. Entrants will be invited
to contribute papers describing their approaches to a special issue of
a technical journal or magazine.
The intended audience is machine learning researchers and professors
currently teaching machine learning classes.
Complete details are available on the contest website:
http://www.cs.utexas.edu/users/sherstov/pdmc
Important dates (tentative)
NOW: Send your expression of interest to the organizers
2 April: Notice of intent to participate due
1 June : Test data set released and announced
18 June : Entry submission deadline
8 July : Workshop/results
------------------------------
From: [email protected]
Subject: Call for Workshop Proposals (IEEE ICDM'04)
Date: 3 Feb 2004 16:54:31 +0900
Call for Workshop Proposals
The 2004 IEEE International Conference on Data Mining (ICDM '04)
Sponsored by the IEEE Computer Society
Brighton, UK
November 1-4, 2004
http://icdm04.cs.uni-dortmund.de
The ICDM '04 organizing committee invites proposals for workshops to
be held in conjunction with the conference. The purpose of these
workshops is to provide participants with an informal setting for
discussing innovative work in progress on important new technical
directions.Workshops will be held on November 1, immediately preceding
the conference on November 2-4.
Researchers and practitioners from all areas of the data mining
community are invited to submit proposals for review. The organizers
of approved workshops are expected to define the workshop's focus,
gather and review submissions, and decide upon final program
content.Although the format of the workshop also is to be determined
by the organizers, substantial time should be allotted for
discussion. Two sucessful workshop formats that worked in the past
(somehow complementary) are: (1) a focused, technical area with a
large enough community to sustain it (e.g. "Techniques and
representations for text clustering"), or a cross-field topic
attractive to reserachers from several sub-communities (e.g. "Privacy
and Security of Genetic and Bioinformatics Data").
The schedule for submission and preparation of workshop papers also
will be left to the discretion of the workshop organizers. Because
ICDM will handle publication of the informal workshop proceedings, we
ask that (1) workshop papers be prepared in the same format as ICDM
conference papers (Latex style file available here), (2) workshop
papers adhere to a 10 page limit (2 pages longer than the conference
limit), and (3) workshop organizers prepare the camera-ready
proceedings by October 15.
IMPORTANT DATES
May 1 Deadline for proposals
May 10 Notification of acceptance
September 15 CR papers for proceedings due
November 1 Workshops at ICDM '04
Submission Procedure
Workshop proposals should be submitted electronically (in Postscript,
PDF or MS Word) to the ICDM '04 Workshops Chair, Stan Matwin.
ADDRESS FOR SUBMISSION
Stan Matwin, ICDM'04 Workshops Chair
University of Ottawa, Ottawa, Canada, K1N6N5
School of Information Technology and Engineering
Email: [email protected]
URL: http://www.site.uottawa.ca/~stan
Tele: +1 613 562 5800 6679
Fax:: +1 613 562 5664
How to Propose a Workshop
Proposals for workshops should be at most five pages in length (fewer
if possible) and should contain:
* A brief description of the specific technical issues that the
workshop will address
* The reasons why the workshop is of interest at this time.
* The names, postal address, phone and fax numbers and email addresses
of the Workshop Organizing Committee. This committee should consist
of at least three experts in the field, not all at the same
institution.
* The name of one member of the Workshop Organizing Committee who is
designated the contact person.
* A list of previously-organized related workshops by any of the
Workshop Organizing Committee. Previous experience organizing
workshops is not a requirement.
* A list of potential attendees.
* A draft workshop Call for Papers.
* A list of audio-visual or technical requirements and any special
room requirements.
Potential workshop proposers may wish to look at web pages from
ICDM'01 Workshops and ICDM'02 Workshops.
------------------------------
From: <[email protected]>
Subject: Computational Creativity workshop - ECCBR 04
Date: Wed, 04 Feb 2004 15:45:01 +0100
FIRST CALL FOR PAPERS - Computational Creativity Workshop
7TH EUROPEAN CONFERENCE IN CASE-BASED REASONING (ECCBR04)
Madrid, Spain, 30 of August till 2 of September, 2004
The Program Committee of the Computational Creativity workshop CC04
invites submissions of technical and position papers for the workshop.
The workshop will be held at Madrid, Spain, as part of the 7TH
European Conference in Case-Based Reasoning (ECCBR04). The
publication of the proceedings of the Workshop is being negotiated
with a publisher.
Workshop Objectives
This workshop will bring together researchers from AI, Cognitive
Science and other related areas such as Psychology, Philosophy and
Arts working on Computational Creativity, providing the opportunity to
promote presentation and discussion of ongoing work in the area.
The workshop should encourage cross-fertilization between the various
approaches, including the study of cognitive and computational models
for Creativity, and the application of current AI techniques to the
development of Creative Systems.
The workshop will provide a forum for identifying trends and
opportunities for research on creativity and promising practices
concerning the development of creative systems.
Topics
Original contributions are solicited in all areas related to Creative
Systems, including but not limited to:
- Computational models of creativity
- Cognitive Science models of creativity
- Machine Creativity
- Evaluation of Creativity
- Metaphor
- Conceptual Combination and Conceptual Integration
- Evolutionary art
- Emotion modelling
- Games and Creativity
Important Dates
May 7, 2004 Submission deadline
June 7, 2004 Notice of Acceptance
July 9, 2004 Deadline for final camera-ready copies
Workshop Format
The workshop will comprise invited talk, presentation and discussion
sessions. An invited talk by a well known researcher in the field is
expected to occur during the first session. The remaining sessions
will consist of paper presentations followed by a discussion panel.
Time will be assigned for each paper presentation, including some time
for discussion. At the end of each day, a slot will be scheduled for a
final discussion.
Submission Requirements for Contributions
Two categories of submissions are welcome: full papers and short
papers.
Full papers must be no longer than 8 pages in length, and are expected
to address foundational issues and research proposals and reports, or
to describe in detail current research on creative systems development
and modelling.
Short papers must be no longer than 4 pages and are expected to
describe ongoing work.
All papers MUST be submitted in Springer LNCS format, which is the
format required for the final camera ready copy. Authors instructions
along with LaTeX and Word macro files are available on the web at
http://www.springer.de/comp/lncs/authors.html.
All Submissions will be made by electronic means, in postscript or PDF
format. Fax, e-mail or snail mail submissions will not be
accepted. Detailed instructions and a submission form will be
available at the workshop web site.
Note: Participants are expected to register for the main ECCBR
conference in addition to the workshop.
Reviewing Process
Submissions will be judged on significance, originality, quality and
clarity. Each paper will be cross-reviewed by at least two referees.
Contributions will be subject to anonymous, blind peer review:
reviewers will not be aware of the identities of the authors. This
requires that authors exercise some care not to identify themselves in
their contributions. Authors will receive feedback in the form of
reviewers' comments.
Proceedings
Accepted contributions will be distributed by the organisation as
workshop notes. Publication of the Proceedings of the Workshop is
being negotiated with a publisher. Further details will be made
available at the website of the workshop as soon as possible.
Workshop Web Site <http://creative-systems.dei.uc.pt/CC04/>
Enquiries Address Email: [email protected]
------------------------------
From: <[email protected]>
Subject: Net.ObjectDays 2004
Date: Fri, 6 Feb 2004 20:41:47 +0100 (CET)
First Call for Papers
Net.ObjectDays 2004
5th Annual International Conference on Object-Oriented and
Internet-based Technologies, Concepts, and Applications for a
Networked World
Erfurt, Germany, September 27-30, 2004
Conference Web Site: www.netobjectdays.org
Important Dates
Submission of Papers: April 23, 2004
Notification: May 28, 2004
Final Version Due: June 25, 2004
Conference: September 27-30, 2004
Net.ObjectDays is one of the major international conferences on
object-oriented and internet-based technologies, concepts, and
applications. Based on a strong research and innovation focus,
Net.ObjectDays has a tradition in bringing together leading
researchers from academia and industry on the one hand and system
architects, developers, and users from industry and administration on
the other hand.
Constantly evolving and increasingly powerful information and
communication technologies have substantially changed the nature of
global relationships, sources of competitive advantage, and
opportunities for economic and social development. The Internet, and
associated communication technologies have turned the globe into an
interconnected network of individuals, firms, organizations, and
governments, communicating and interacting with each other through a
variety of channels.
These developments pose increasingly complex challenges to the
computer science community in general and the software community in
particular. One of the most important aspects is characterized by
buzzwords like on-demand computing or adaptable computing. The basic
idea is to assemble, configure and compose software at runtime to
provide individual solutions to solve one-of-a-kind issues in an
adequate, reliable and cost-effective way.
Given this background, the focus of Net.ObjectDays 2004 is on methods,
concepts, languages, and tools for efficient, reliable and adaptive
composition of software artefacts to provide value-added services,
i.e., to provide the scientific and technological basis for making
on-demand computing a reality.
Recent developments in different areas contribute to this
technological basis, for instance web services, service composition
and grid computing, but also in software generation, domain
engineering and related approaches. Along this line, the topics of the
conference include but are not limited to:
- Software Methodologies for service composition
- Semantic Web Services
- Ontological Engineering
- Grid Services infrastructure
- Functional and non-functional properties
- Service Registry design
- Standardization issues
- Framework technologies and platform developments
- Software Reusability
- Domain Engineering and Software Product Lines
- Object-oriented technologies and concepts
- Architecture-centric development
- Component-based approaches
- Agile Processes and Agile Modeling
- Generic Programming
- Model Driven Architecture
- Software Patterns and Frameworks
- Software Quality and Testing
- Aspect-Oriented Software Development
- Generative Programming
- Component Market Places
- Middleware, especially EJB, CORBA, Web Services,
.NET, Jini
We invite submissions in the following categories:
- Research papers
- Case studies from industry
Electronic submissions are strongly encouraged; please upload a
self-contained PostScript file or PDF file; details will be announced
shortly.
Papers must be original contributions that have not been published
previously, nor already submitted to other conferences in parallel
with this conference. The length of the paper cannot exceed 16 pages,
and the paper should be in such a form that it can be immediately
included in the proceedings without major revision. The layout has to
match the formatting instructions of Springer LNCS that can be found
at www.springer.de/comp/lncs/authors.html. Papers that do not match
these formatting instructions will not be considered. Papers must be
in English. Submissions received too late and submissions sent by fax
will not be considered.
The title page must contain a short abstract and a classification of
the topics covered, preferably based on the topics above. Please also
specify the paper category. The paper must clearly state the problem
being addressed, the goal of the work, the results achieved, and the
relation to other work. It must be self contained.
For more information, visit www.netobjectdays.org
------------------------------
From: "ITS" <[email protected]>
Subject: ITS 2004 Call for Workshop Proposals
Date: Fri, 6 Feb 2004 17:53:08 -0500
ITS 2004 Call for Workshop Proposals and Tutorial Proposals
The ITS 2004 Workshops and Tutorials Chairs invite proposals for workshops
and tutorials to be held 30-31 August 2004 in conjunction with the 7th
International Conference on Intelligent Tutoring Systems in Maceió,
Alagoas, Brasil (see <http://www.itsconference.org/2004>).
Submit a workshop or tutorial proposal in Word or HTML in the form of an
announcement ready to post on the ITS2004 website, including:
* Title of workshop or tutorial
* Preferred duration (half or full day)
* Information about organizer(s): name, title, affiliation, address,
phone, email
* Objectives to be achieved
* Scope of topics to be addressed
* Target audience
* Format and schedule (allow ample time for discussion, especially in
workshops!)
* Audiovisual resources requested
* Anything else attendees should know
Workshop proposals should also include:
* Organizing/review committee
Tutorial proposals should also include:
* Background knowledge expected from the participants
* An abstract of approximately 200 words
* Table of contents (one page)
* Relevant qualifications of instructor(s). We encourage co-teaching
by multiple instructors with different perspectives.
Besides the announcement, also provide:
* Evidence of interest, such as a list of people who have said they
are likely to participate or to send students.
IMPORTANT DATES (updates at <http://www.itsconference.org/2004>)
* PROPOSALS DUE: March 10
* Organizers notified: March 24
* Announcements posted: March 26
* Workshop papers due: May 5
* Workshop authors notified: May 31
* Camera-ready papers due: June 30
* Workshop proceedings due: July 15
* Tutorial handouts due: July 30
(Local ITS2004 conference organizers will print workshop proceedings and
tutorial handouts.)
Please email your proposals (or questions) to both of us. Include "ITS
2004 Proposal" in the Subject: line. We look forward to them!
The ITS 2004 Workshops and Tutorials Chairs:
Jack Mostow
Carnegie Mellon University, USA
[email protected] <mailto:[email protected]>
Patricia Tedesco
Federal University of Pernambuco, Brasil
[email protected] <mailto:[email protected]>
------------------------------
From: Vitorino RAMOS <[email protected]>
Subject: Swarm Intelligence and Patterns (SIP'04)
Date: Sat, 07 Feb 2004 16:06:55 +0000
SWARM INTELLIGENCE AND PATTERNS (SIP'04) - Call for Papers
Web site: http://alfa.ist.utl.pt/~cvrm/staff/vramos/SIP.html
Int. Workshop Session at ISDA'04 - 4th International Conference on
Intelligent Systems, Design and Applications.
Conference dates: August 26-28, 2004.
Location: Budapest,Hungary.
IMPORTANT DATES:
Paper submission Due (full paper) : April 1, 2004
Notification of acceptance: May 10, 2004
Camera ready papers and authors' registration : June 10, 2004
Conference - August 26-28, 2004. Budapest, Hungary.
SCOPE AND CALL FOR PAPERS:
Self-organizing intelligent complex systems typically are comprised of
a large number of frequently similar components or events. Through
their process, a pattern at the global-level of a system emerges
solely from numerous interactions among the lower-level components of
the system. Moreover, the rules specifying interactions among the
system's components are executed using only local information, without
reference to the global pattern, which, as in many real-world problems
is not easily accessible or possible to be found. Stigmergy, a kind
of indirect communication and learning by the environment found in
social insects is a well know example of self-organization, providing
not only vital clues in order to understand how the components can
interact to produce a complex pattern and engineer applications, as
can pinpoint simple biological non-linear rules and means to achieve
an improved design of artificial intelligent systems.
SWARM INTELLIGENCE is precisely a relatively novel discipline devoted
to the study of self-organizing collective processes in Nature and
Human artefacts as well as on their applications. An example of
particularly successful research direction in swarm intelligence is
ant colony optimization (ACO), which focuses on discrete optimization
problems, and has been applied successfully to a large number of hard
discrete optimization problems including the travelling salesman, the
quadratic assignment, scheduling, vehicle routing, etc., as well as to
routing in telecommunication networks.
However, apart from the remarkable successful applications in
optimization as well as on their critical features as a bio-inspired
computational paradigm, a small number of works have still been
devoted to Data Classification and Retrieval Systems, Clustering,
Pattern Recognition, Distributed Data-Mining, Web Mining and GRIDS,
Collaborative Filtering, Image Analysis and Signal Processing, Pattern
Formation, Perception, Memory and Generalization. At the present
section we seek to explore the applicability of these bio-inspired
approaches to the development of self-organizing, evolving, adaptive
and autonomous information technologies, which will meet the
requirements of next-generation information systems, such as
diversity, scalability, robustness, and resilience.
TOPICS OF INTEREST:
Topics of interest include, but are not limited to, applications and
theory dealing with any aspect of Swarm Intelligence, Pattern
Recognition, Data and Image Processing, as:
- Intelligent Systems Design.
- Advanced Signal and Image processing algorithms.
- Pattern Recognition and Emergent Behaviour.
- Data Categorization, Visualization. Data and Knowledge Extraction /
Representation.
- Feature Extraction and Selection. Unsupervised Learning.
- Information Systems.
- Collective Intelligence and Search. Exploring versus Exploiting.
- Artificial Habitats and Information.
- Exploratory Data Analysis. Data-Mining.
- Cognition, Interactivity, Signals and Communication.
- Bottom-up Strategies and Non-Hierarchical Systems.
- Adpative Systems and Self-Configuration.
- Mapping Concepts, Cognitive Maps and Self-Organizing Maps.
- Complex Adaptive Systems.
- Stigmergy, Self-Organization, Metamorphosis, Emergence and
Co-Evolution.
- Artificial Life as well as other Animal Societies bio-inspired
algorithms.
- Artificial Societies and Web-based Communities.
- Wireless Communication, Cellular Systems, Indirect Communication
through artefacts.
- Social Networks and New Media.
- Artificial Immune Systems and Self-Organization.
- Classification, Sorting, Data Retrieval, Clustering.
- Web Mining, Semantic Web, Collaborative Mining, GRIDS, Network
security.
- Auto-Catalysis, Positive and Negative Feedbacks, Cybernetics.
- Swarm and Cooperative Robotics.
- Distributed algorithms, self-regulation, self-repair and
self-maintenance ontologies.
- Biomedical, multimedia and e-commerce applications.
- Collective on-line Games. iDesign, Active aLif(v)e Art and e-Artefacts.
- Generative and Computational Art.
- Hybridization with other methods (e.g. Evolutionary Computation and
Neural Networks).
PAPER SUBMISSION:
All accepted papers should follow IEEE format (check ISDA Call for
Papers). Submitted papers have to be original, 6 pages long,
containing new and original results.
Author's guidelines and format instructions can be downloaded from the
following links:
http://alfa.ist.utl.pt/~cvrm/staff/vramos/SIP.html and
http://www.cs.okstate.edu/~isda04/submission.html .
Please send the full paper as an email attachment to:
Vitorino Ramos [email protected] with
a cc to [email protected]
------------------------------
From: "Baowen Xu" <[email protected]>
Subject: WEBSA2004: 2nd Int'l Workshop on Web Based Systems and Applications (WEBSA2004)
Date: Sat, 7 Feb 2004 21:24:47 +0800
Second International Workshop on
Web Based Systems and Applications (WEBSA2004)
http://cse.seu.edu.cn/people/bwxu/websa2004
in conjunction with
COMPSAC 2004
September 28-30, 2004, Hong Kong
http://rachel.utdallas.edu/compsac
Motivation
The open approaches to develop web-based systems and applications have
attracted an increasing attention in both academia and industry. In
order to ensure the quality of web-based systems and applications,
this workshop will not only focus on models and architectures for
web-based systems, but also emphasize the emerging technology in
analyzing and testing web-based applications, which will be held
together with COMPSAC 2004 (http://rachel.utdallas.edu/compsac/ ).
The aim of this workshop is to bring together researchers and
practitioners working on theories, techniques and applications,
concerning analysis and/or testing of web-based systems. The complex
and large-scale web-based systems require effective methodologies and
tools for their analysis, testing, maintenance and evolution.
Scope of the Workshop
The workshop emphasizes on the analysis and testing techniques
concerned with the quality of the web-based systems and
applications. The program will consist of invited papers, contributed
papers and possible working sessions. Topics include, but not limited
to:
Architecture and Models
- Web Application Models
- Adaptive Web systems
- Semantic Web and Ontology Engineering
- OO Technology and Component-based Web Engineering
Methods and Tools
- Security and Accessibility in Web Applications
- Proxy, Search and Cache Techniques
- Neural Networks, Fuzzy Logic, Rough Sets, and Evolutionary Computation
- Lightweight and Web-based Tools
Quality Assurance
- Cooperation and Integration
- Web-Based System Testing and Evolution
- Measurements for Web-Based Software Development
Original papers on new results in the rapidly emerging area --
web-based systems and their applications especially in analyzing and
testing technology are preferred. Papers should indicate the
innovative aspects of the results and the contribution to the
fields. Papers submitted for publication in a journal or another
conference will not be considered.
Important Dates
Paper submissions due: March 15, 2004
Notification of acceptance: May 20, 2004
Camera-ready Due: June 30, 2004
Submission
All contributed papers will be reviewed following the same schedule
and criteria as for the COMPSAC 2004 submissions. The workshop will be
open to all COMPSAC attendees interested in these topics.
Papers must be submitted electronically at
http://rachel.utdallas.edu/compsac/submit.html. Please read and follow
the instructions listed on that page. The format of submitted papers
must follow the IEEE conference proceedings guidelines which are
available at http://computer.org/author/psguide.htm. Accepted papers
will be included in a separate proceedings. Each paper is expected to
be no more than four pages. One of the authors of each accepted paper
must present the paper at the workshop and have regular registration
uniquely identified with the paper, which will cover the following:
the admission to all the technical sessions and a copy of the
proceedings of COMPSAC 2004 and its workshops, the welcome reception
and conference banquet.
For updated information, please refer to
http://rachel.utdallas.edu/compsac or contact Professor Baowen Xu (
[email protected] ).
------------------------------
From: Yaneer Bar-Yam <[email protected]>
Subject: ICCS Deadline Extension for Abstract Submission
Date: Wed, 4 Feb 2004 09:48:39 -0500
Preliminary Program and Abstract Submission Deadline Extension
for the
International Conference on Complex Systems
with special sessions on Engineering Complex Systems
Because of a delay in the program committee meeting the ICCS abstract
submission deadline has been extended to February 15. After this date,
abstracts will be accepted only if space is available in specific
sessions. The early registration deadline has been extended to March
1.
Registering to attend the conference without giving a presentation is
also still possible.
Students and postdocs should submit papers about recent advances in
their research. Generally, they will be given opportunities to give
short talks or, if they prefer, poster presentations. We expect to
have funds to assist students and postdocs in attending the
conference.
Preliminary conference program and further details available on the
conference web page at:
http://www.necsi.net/events/iccs/iccscover.html
------------------------------
From: Stefano Basagni <[email protected]>
Subject: MobiQuitous 04: Extended paper submission deadline
Date: Wed, 4 Feb 2004 18:10:12 -0500 (EST)
MobiQuitous 2004
http://www.mobiquitous.org
The First Annual International Conference on
Mobile and Ubiquitous Systems: Networking and Services
August 22-25, 2004 Boston, Massachusetts, USA
The combination of mobile and ubiquitous computing is emerging as a
promising new paradigm with the goal to provide computing and
communication services all the time, everywhere, transparently and
invisibly to the user, using devices embedded in the surrounding
physical environment. In this context, the communication devices, the
objects with which they interact, or both may be mobile. The
implementation of such a paradigm requires advances in wireless
network technologies and devices, development of infrastructures
supporting cognitive environments, and discovery and identification of
ubiquitous computing applications and services. The first ACM Annual
International Conference on Mobile and Ubiquitous Systems: networking
and services (Mobiquitous 04) will cover all these aspects,
representing a forum where practitioners and researchers coming from
the many areas involved in ubiquitous solutions design and deployment
will be able to interact exchanging the cross-layer experiences needed
to build the overall ubiquitous systems. Areas addressed by the
conference include: applications, service-oriented computing,
middleware, networking, agents, knowledge management and databases.
(Visit the conference site for details.)
IMPORTANT DATES
Paper registration deadline: FEBRUARY 14 2004, 11:59pm PST
Paper submission deadline: **NEW** FEBRUARY 16 2004, 11:59pm PST
Notification of acceptance: APRIL 30 2004
Camera-ready version due: MAY 15 2004
Papers submitted to MobiQuitous 2004 must be registered with
EDAS by 11:59pm, PST, February 14, 2004. The deadline for
submitting a registered paper is 11:59pm, PST, February 16, 2004.
------------------------------
From: Zhaoping Li <[email protected]>
Subject: Postdoc in vision/neuroscience in University College London
Date: Mon, 26 Jan 2004 17:05:16 +0000
Research Fellow
Applications are invited for the post of Postdoctoral Research Fellow
to work with Dr. Li Zhaoping (http://www.gatsby.ucl.ac.uk/~zhaoping)
in the area of neuroscience, particularly on biological vision, using
theoretical and/or psychophysical investigation tools. The candidate
should have good experience in theoretical/modelling area or in visual
psychophysical area.
Interest and capability to engage in research activities in both areas
would be preferable although not essential. The research fellow is
expected to contribute to the research environment of the laboratory
and should have the capability to work well in a team. The post is
available for two years and may be extended. Salary is on the RA1A
scale (A323,259-29,473 including London allowance) and will depend
upon qualifications and experience.
We particularly welcome women and black and ethnic minority applicants
as they are under represented at this level within University College
London (s.48 of the SDA 1975/s.38 of the RRA 1976 apply).
Applications (e-mail or hard copy) by covering letter, CV and Personal
Information form (the latter available at:
http://www.psychol.ucl.ac.uk/info/Personal_Information.doc) to John
Draper,
Departmental Administrator, Department of Psychology, UCL, Gower
Street, London WC1E 6BT, UK, [email protected]. If applying by e-mail
please submit all requested information in one .pdf file named by your
surname eg
Smith.pdf. Further information concerning the post are on the web at:
http://www.psychol.ucl.ac.uk/info/psychophysics_li.htm while
interested candidates can also contact Li Zhaoping, [email protected], 44
20 7679 1174.
------------------------------
From: [email protected]
Subject: R&D jobs in watermarking, biometrics, HCI, medical imaging, image/video processing
Date: Tue, 3 Feb 2004 12:12:54 +0200
Research Positions at AIIA Lab, Greece
The applicants must be citizens of EU or of associated countries.
The Artificial Intelligence and Information Analysis (AIIA) Laboratory
at the Department of Informatics of the Aristotle University of
Thessaloniki, Greece is seeking for candidates to fill a number of
vacant research positions:
* Postdoctoral researchers.
* Researchers at the level of Diploma of Electrical Engineering /
Computer Science / Computer Engineering or equivalent. The applicants
can work towards a PhD degree, while occupying these positions, if
desirable.
* Support engineers (C, C++ programming, Data base programming, WWW
design, e-commerce/marketing).
The AIIA Lab profile and related infos can be found in
<http://poseidon.csd.auth.gr/>http://poseidon.csd.auth.gr. The
positions are funded by several competitive FP6 R&D projects (Networks
of Excellence and Integrated projects funded European Union). The
general research topic is digital signal / image / video processing
and analysis, computer vision, graphics, biomedical imaging,
bioinformatics. An indicative list of possible research topics is the
following:
* Multimedia copyright protection/ Watermarking
* Bioinformatics
* Medical Image Processing
* Multimodal interfaces, affective computing, gesture recognition
* Biometrics and Face Verification
* Multimedia, Human-Computer Interaction and Virtual Reality,
* Image/Video Processing and Analysis
* Data Mining and Retrieval from image/video databases
The exact research topic of the new researcher will be chosen so as to
match his/her experience aiming at maximum productivity. The positions
are financed by EU research projects. Appointments can be extended for
3 years or more. Proven research experience in one of the following
fields: digital image processing, computer vision, graphics,
interfaces, biomedical, very good knowledge of English, C/C++
programming and strong interest in academic research are highly
desired.
The applicants must be citizens of EU or of associated countries.
Prospective applicants should forward their resume (CV) and
recommendation letters by fax or email (preferably) to:
Prof. Ioannis Pitas
Department of Informatics
Aristotle University of Thessaloniki
Thessaloniki 54124, Box 451
GREECE
Tel: +30-2310-996304
Fax: +30-2310-996304
e-mail: [email protected]
------------------------------
From: [email protected]
Subject: Advanced Course in Computational Neuroscience 2004
Date: Fri, 30 Jan 2004 12:01:54 +0100
ADVANCED COURSE IN COMPUTATIONAL NEUROSCIENCE
(AN IBRO NEUROSCIENCE SCHOOL)
August 16th - September 10th, 2004
MUNICIPALITY OF OBIDOS, PORTUGAL
DIRECTORS: Ad Aertsen (University of Freiburg, Germany)
Peter Dayan (University College London, UK)
Alain Destexhe (CNRS, Gif-sur-Yvette, France)
Eilon Vaadia (Hebrew University, Jerusalem, Israel)
The Advanced Course in Computational Neuroscience introduces students
to the panoply of problems and methods of computational neuroscience,
addressing issues of neural organization from sub-cellular to network
and inter-areal levels.
The course has two complementary parts. Mornings are devoted to
lectures given by distinguished international faculty on topics across
the breadth of experimental and computational neuroscience. During the
rest of the day, students are given practical training in the art and
practice of neural modeling, largely through the medium of their
individual choice of model systems.
The first week of the course introduces students to essential
neurobiological concepts and to the most important techniques in
modelling single cells, networks and neural systems. Students learn
how to solve their research problems using software packages such as
GENESIS, MATLAB, NEST, NEURON, XPP, etc. During the following three
weeks the lectures cover specific brain areas and functions. Topics
range from modelling single cells and subcellular processes through
the simulation of simple circuits, large neuronal networks and system
level models of the brain. The course ends with project presentations
by the students.
The Advanced Course in Computational Neuroscience is designed for
advanced graduate students and postdoctoral fellows in a variety of
disciplines, including neuroscience, physics, electrical engineering,
computer science, mathematics and psychology. Students are expected to
have a keen interest and basic background in neurobiology as well as
some computer experience. Students of any nationality can apply.
A maximum of 30 students will be accepted. There will be a fee of EUR
800,- per student covering costs for lodging, meals and other course
expenses. Depending on funding, there will be a limited limited
number of tuition fee waivers and travel stipends available for
students who need financial help for attending the course. We have
received IBRO funding to provide full travel and fee support for 4-5
students from developing countries. These students will be accepted
according to the normal selection procedure. We specifically encourage
applications from researchers who work in the developing world.
Applications, including a description of the target project must be
submitted electronically (see below) and should be accompanied by two
letters of recommendation (also sent electronically). Applications
will be assessed by a committee, with selection being based on the
following criteria: the scientific quality of the candidate (CV) and
of the project, the letters, and evidence that the course affords
substantial benefit to the candidate's training.
More information and application forms can be obtained from:
http://www.neuroinf.org/courses/EUCOURSE
Please apply electronically using a web browser.
Contact address:
- mail: Camilla Bruns, FR2-1, Fakultaet IV, Technical University
of Berlin, Franklinstrasse 28/29, 10587 Berlin, Germany
- e-mail: [email protected]
APPLICATION DEADLINE: April 23, 2004
DEADLINE FOR LETTERS OF RECOMMENDATION: April 30, 2004
Applicants will be notified of the results of the selection procedures by
end of May 2004.
------------------------------
From: Eric Baum <[email protected]>
Subject: What is Thought?: Book announcement
Date: Sun, 1 Feb 2004 07:43:58 -0500
New Book:
What is Thought?
Eric B. Baum
MIT Press 478p
This reports on a 10+ year project to see whether what I viewed as the
worldview of the connectionist/COLT community could extend in any
plausible way to explain all the capabilities of mind. I found such an
extension, but only after being constrained into conjectures that are
at odds with what I would have expected.
*What is Thought?* proposes a model that explains how mind is
equivalent to execution of a computer program, addressing aspects such
as understanding, meaning, creativity, language, reasoning, learning,
and consciousness, that is consistent with extensive data from a
variety of fields, and that makes empirical predictions. Meaning is
the computational exploitation of the compact underlying structure of
the world, and mind is execution of an evolved program that is all
about meaning. Occam's Razor, as formalized in the recent computer
science literature, is explained and extrapolated to argue that
meaning results from finding a compact enough program behaving
effectively in the world; such a program can only be compact by virtue
of code reuse, factoring into interacting modules that capture real
concepts and are reused metaphorically. For a variety of reasons,
including arguments based on complexity theory, developmental biology,
evolutionary programming, ethology, and simple inspection, this
compact Occam program is most naturally seen to be in the DNA, rather
than the brain. Learning and reasoning are then fast and almost
automatic because they are constrained by the DNA programming to deal
only with meaningful quantities. Evolution itself is argued to exploit
meaning in related ways. Words are labels for meaningful computational
modules. Using the abilility to pass along programs through speech,
humans have made cumulative progress in constructing, as part of their
minds, useful computational modules built on top of the ones supplied
by evolution. The difference between human and chimp intelligence is
largely in this additional programming, and thus can be regarded as
due to better nurturing. Human written computer programs, however, are
generally not highly compressed and thus don't display understanding
in the same way as human thought, but experiments are described in
which modular computer programs were evolved that achieve abilities
giving insight into how programs can evolve understanding.
The many aspects of consciousness are also naturally and consistently
understood in this context. For example, although the brain is a
distributed system and the mind is a complex program composed of many
modules, the unitary self emerges naturally as a reification
(manifestation) of the interest of the genes. Qualia (the sense of
experience of sensations such as pain or redness) have exactly the
appropriate nature and meaning that evolution coded in the DNA so that
the compact program behaves effectively.
No previous familiarity with computer science (or other fields) is
assumed-- *What is Thought?* presents a pedagogical survey of the
relevant background for its arguments.
------------------------------
From: Methods for Modalities <[email protected]>
Subject: ESSLLI 2004: Preliminary Announcement
Date: Sun, 1 Feb 2004 15:17:02 +0100
Preliminary Announcement
ESSLLI 2004
Nancy, France 9-20 August, 2004
ESSLLI 2004, the 16th European Summer School in Logic, Language and
Information will be held in Nancy, France 9-20 August, 2004. It is
being hosted by LORIA (the Laboratoire lorrain de recherche en
informatique et ses applications) and will be held on the Campus
Scientifique of the University of Nancy 1 (University Henri Poincare).
ESSLLI is the annual summer school of FoLLI, the European Association
for Logic, Language and Information. Like previous ESSLLIs, ESSLLI
2004 will offer a two week program of foundational lectures,
introductory lectures, advanced lectures, and workshops. All in all,
48 lectures and workshops will be offered. You can find more
information, including a timetable, at the ESSLLI 2004 website:
http://esslli2004.loria.fr
Registration for ESSLLI 2004 is not yet open, but on this website you
will already find preliminary information about registration,
accomodation and prices. An email announcement will be sent around
when registation opens.
We look forward to seeing you in Nancy this August!
Carlos Areces, Patrick Blackburn (for the organising committee)
Helene Kirchner (Director of Loria)
------------------------------
End of ML-LIST Digest Vol 16, No. 3
***********************************