Machine Learning List: Vol. 16, No. 6 Saturday, March 27, 2004
Contents Calls for Papers/Participation AP2PC'2004: 3rd Int'l Workshop on Agents and Peer-to-Peer Computing INTELLIGENT DATA ANALYSIS IN MEDICINE AND PHARMACOLOGY AAMAS-04 Workshop on Learning and Evolution in Agent Based Systems PAKM2004: Practical Aspects of Knowledge Management Mass Customization and Personalization Forum 2004 AI-2004: 17th Australian Joint Conference on Artificial Intelligence ICDL 04: 3rd Int'l Conf. on Development and Learning 24th Urban Data Management Symposium SASEMAS 2004: CFP IEEE TEC: Special Issue on Analysis and Design of Representations Other Meeting Announcements CEC 2004 Contests Deadline Extended: GECCO Workshop on Adaptation, Approximation, ... Deadline Extended: GECCO Workshop on Self-organization in ... Deadline Extended: LOFT6 ICML-04 Tutorial and Workshop Program Career Opportunities Career Opportunities Program Leader: Symbolic Machine Learning and Knowledge Acquisition Open Position---Fulltime Scientific Software Engineer Miscellaneous Announcements automatic clustering of all 702 MLJ articles 6th European Agent Systems Summer School: CFP New issues of cognitive systems research 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: "Gianluca Moro" <[EMAIL PROTECTED]> Subject: AP2PC'2004: 3rd Int'l Workshop on Agents and Peer-to-Peer Computing Date: Sat, 6 Mar 2004 21:01:15 +0100 CALL FOR PAPERS Third International Workshop on AGENTS AND PEER-TO-PEER COMPUTING (AP2PC 2004) http://p2p.ingce.unibo.it/ New York City, USA July 19, 2004 to be held at AAMAS 2004 Third International Joint Conference on Autonomous Agents and MultiAgent Systems IMPORTANT DATES Abstract: 1st April 2004 Paper submission: 6th April 2004 Acceptance notification: 1st May 2004 Workshop: 19th July 2004 Camera ready for Post-proceedings: 31st August 2004 Publisher: Springer, series Lecture Notes in Computer Science OVERVIEW Peer-to-peer (P2P) computing is attracting enormous media attention, spurred by the popularity of file sharing systems such as Napster, Gnutella, and Morpheus. The peers are autonomous, or as some call them, first-class citizens. P2P networks are emerging as a new distributed computing paradigm for their potential to harness the computing power of the hosts composing the network and make their under-utilized resources available to others. This possibility has generated a lot of interest in many industrial organizations which have already launched important projects. In P2P systems, peer and web services in the role of resources become shared and combined to enable new capabilities greater than the sum of the parts. This means that services can be developed and treated as pools of methods that can be composed dynamically. The decentralized nature of P2P computing makes it also ideal for economic environments that foster knowledge sharing and collaboration as well as cooperative and non-cooperative behaviors in sharing resources. Business models are being developed, which rely on incentive mechanisms to supply contributions to the system and methods for controlling free riding. Clearly, the growth and the management of P2P networks must be regulated to ensure adequate compensation of content and/or service providers. At the same time, there is also a need to ensure equitable distribution of content and services. Although researchers working on distributed computing, MultiAgent Systems, databases and networks have been using similar concepts for a long time, it is only recently that papers motivated by the current P2P paradigm have started appearing in high quality conferences and workshops. Research in agent systems in particular appears to be most relevant because, since their inception, MultiAgent Systems have always been thought of as networks of peers. The MultiAgent paradigm can thus be superimposed on the P2P architecture, where agents embody the description of the task environments, the decision-support capabilities, the collective behavior, and the interaction protocols of each peer. The emphasis in this context on decentralization, user autonomy, ease and speed of growth that gives P2P its advantages, also leads to significant potential problems. Most prominent among these problems are coordination: the ability of an agent to make decisions on its own actions in the context of activities of other agents, and scalability: the value of the P2P systems lies in how well they scale along several dimensions, including complexity, heterogeneity of peers, robustness, traffic redistribution, and so on. It is important to scale up coordination strategies along multiple dimensions to enhance their tractability and viability, and thereby to widen the application domains. These two problems are common to many large-scale applications. Without coordination, agents may be wasting their efforts, squander resources and fail to achieve their objectives in situations requiring collective effort. This workshop will bring together researchers working on agent systems and P2P computing with the intention of strengthening this connection. Researchers from other related areas such as distributed systems, networks and database systems will also be welcome (and, in our opinion, have a lot to contribute). We seek high-quality and original contributions on the general theme of agents and P2P computing. The following is a non-exhaustive list of topics of special interest: * Intelligent agent techniques for P2P computing * P2P computing techniques for multi-agent systems * The Semantic Web, Semantic Coordination Mechanisms and P2P systems * Scalability, coordination, robustness and adaptability in P2P systems * Self-organization and emergent behavior in P2P networks * E-commerce and P2P computing * Participation and Contract Incentive Mechanisms in P2P Systems * Computational Models of Trust and Reputation * Community of interest building and regulation, and behavioral norms * Intellectual property rights in P2P systems * P2P architectures * Scalable Data Structures for P2P systems * Services in P2P systems (service definition languages, service discovery, filtering and composition etc.) * Knowledge Discovery and P2P Data Mining Agents * P2P data management * Information ecosystems and P2P systems * Security issues in P2P networks * Pervasive computing based on P2P architectures (ad-hoc networks, wireless communication devices and mobile systems) * Grid computing solutions based on agents and P2P paradigms * Legal issues in P2P networks FOR MORE INFORMATION, visit http://p2p.ingce.unibo.it/ ------------------------------ From: "blaz" <[EMAIL PROTECTED]> Subject: INTELLIGENT DATA ANALYSIS IN MEDICINE AND PHARMACOLOGY Date: Mon, 8 Mar 2004 08:12:15 +0100 INTELLIGENT DATA ANALYSIS IN MEDICINE AND PHARMACOLOGY Stanford University, U.S.A., September 6, 2004 http://idamap.org/idamap2004 Call For Papers IMPORTANT DATES Submission of papers: June 5, 2004 Notification: June 28, 2004 Camera-ready: July 30, 2004 GENERAL INFO IDAMAP-2004 is the ninth workshop on intelligent data analysis in medicine and pharmacology and will be held just prior to MEDINFO Conference. The IDAMAP workshop series is devoted to computational methods for data analysis in medicine, biology and pharmacology that present results of analysis in the form communicable to domain experts and that somehow exploit expert knowledge of the problem domain. Typical methods include data mining, temporal abstraction, machine learning, and data visualization. Gathering in an informal setting, workshop participants will have the opportunity to meet and discuss selected technical topics in an atmosphere which fosters the active exchange of ideas among researchers and practitioners. The workshop is intended to be a genuinely interactive event, thus ample time will be allotted for general discussion. The workshop will feature two invited talks. Michael Kattan from Memorial Sloan-Kettering Cancer Center in New York will give a talk on cancer prediction models and their utility in clinical practice, and Marco Ramoni from Harvard Medical School in Boston will talk on Bayesian networks for integrative genomics. WORKSHOP TOPICS The workshop topics include but are not limited to: - data mining techniques, including machine learning, clustering, neural networks, SVM, etc. - other techniques for predictive modeling, - data visualization, - analysis of large data sets, - relational data mining, - interpretation of time-ordered data, - knowledge representation and management, - utility of background knowledge, - integration of intelligent data analysis techniques within biomedical information systems. PROGRAM, SUBMISSIONS AND REGISTRATION The scientific program of the workshop will consist of presentations of invited and accepted papers and panel discussion. Paper submissions addressing the methodological issues relevant to the workshops as well as papers describing particular biomedical applications or data analysis tools are invited. For details on registration, and submission and preparation of papers see workshop's web page (http://idamap.org/idamap2004). Accepted papers will be published as workshop notes. A subsequent publication of selected and revised papers in peer-reviewed journal is planned. CONTACT PERSON Blaz Zupan University of Ljubljana, Slovenia E-mail: [EMAIL PROTECTED] ------------------------------ From: Sandip Sen <[EMAIL PROTECTED]> Subject: AAMAS-04 Workshop on Learning and Evolution in Agent Based Systems Date: Wed, 10 Mar 2004 14:57:57 -0600 (CST) AAMAS-04 Workshop on "Learning and Evolution in Agent Based Systems" Researchers in machine learning and adaptive systems have been addressing issues concerned with learning and adapting from past experience, observation, failures, etc. Whereas most of this research has focused on techniques for acquisition and effective use of problem solving knowledge from the viewpoint of a single autonomous agent, recent investigations have opened the possibility of application of some of these techniques in multiagent settings. The goal of this workshop is to focus on research that will address unique requirements for agents learning and adapting to their environment. Recognizing the applicability and limitations of current machine learning research when applied to situated agents will be of particular relevance to this workshop. The workshop will also encourage presentation and discussion of ideas relating to evolutionary learning and adaptation techniques in the context of agent based systems. Expected contributions include both evolutionary learning by individual agents as well as evolutionary design of agent societies. Of particular interest is new models for coevolving agent populations. We solicit research contributions that address new learning modalities, e.g., the use of communication to enhance learning. Presentation of applications of learning in key multiagent problems like negotiation, teamwork, trust, auctions, supply chains, etc. are welcome. We focus on three different ways in which machine learning can be used to enhance the performance of an Agent Based System: -- An agent can learn the preferences and changing priorities of associated users. -- An agent can learn about other agents in the environment in order to compete and/or cooperate with them. An agent can learn from other agents, taking advantage of their experiences and incorporating these into its own knowledge base. -- An agent can learn about other regularities in its environment. TOPICS OF INTEREST We would particularly welcome new insights into these problems from other related disciplines and thus would like to emphasize the inter-disciplinary nature of the workshop. Among others, papers of the following kind are welcome: 1) Evaluation of the effectiveness of individual learning strategies (e.g., case-based, explanation-based, inductive, reinforcement), or multistrategy combinations. 2) Characterization of learning and adaptation methods in terms of modeling power, communication abilities, knowledge requirement, processing abilities of individual agents. 3) Developing learning and adaptation strategies, or reward structures, for environments with cooperative agents, selfish agents, partially cooperative (will cooperate only if individual goals are not sacrificed) and for environments that can contain mixture of these types of agents. 4) Analyzing convergence properties of existing algorithms and constructing algorithms that guarantee convergence and stability of group behavior. 5) Evaluating effects of knowledge acquisition mechanisms on responsiveness of agents or groups to changes in the agent population in the environment. 6) Learning to work as an effective team by taking advantage of complementary skills and resources. 7) Agents learning via passive or non-intrusive observation of user behaviors or by mimicking other agents. 8) Evolving agent behaviors or co-evolving multiple agents with similar/opposing interests. 9) Investigation of teacher-student relationships between agents or between an agent and the associated user. 10) Applications of learning agents including agents that learn to negotiate contracts, learning trustworthiness of other agents, learn to detect security threats, etc. SUBMISSION REQUIREMENTS: E-mail the URL of either a -- brief statement of interest (1 page), -- complete paper (3000 words maximum) including keywords and authors' complete address to Sandip Sen at [EMAIL PROTECTED] Papers and statement of interest must either be in postscript or pdf format. NOTE: You should send an URL for retrieving the papers, not the actual paper (if this is a problem, please contact Sandip Sen at [EMAIL PROTECTED]). IMPORTANT DATES: Deadline for paper submission: April 19, 2004 Acceptance notice to participants: May 17, 2004 Camera-ready papers due: May 31, 2004 ------------------------------ From: "pakm2004" <[EMAIL PROTECTED]> Subject: PAKM2004: Practical Aspects of Knowledge Management Date: Mon, 15 Mar 2004 12:51:00 +0100 5th International Conference on Practical Aspects of Knowledge Management www.dke.univie.ac.at/pakm2004 2-3 December 2004, Vienna, Austria AIMS AND SCOPE: To succed in a world characterisied by the accelerating pace of the "internet age", organisations must efficiently leverage their most valuable and underleveraged resource: the intellectual capital of their highly educated, skilled, and experienced employees. The compression of communication cycles and the omnipresence of information forces enterprises to seek a faster return on knowledge - knowledge that ages rapidly in a market place brimming with innovation. PAKM2004 addresses all aspects of Knowledge Management and their role in next-generation business solutions. We seek original contributions in the triangle of business and organization sciences, cognitive science, and computer science that represent a true advancement beyond the state-of-the-art of Knowledge Management: a. Building and maintaining knowledge inventories - knowledge directories - automatic creation of semantic annotations - skill management b. Collaboration and knowledge sharing - social and cultural aspects of knowledge sharing communities - collaboration platforms - integration of processes across organizational boundaries c. Capturing and securing knowledge - knowledge capturing within business processes - lessons learned and debriefing - organizational memories d. Knowledge utilization - content-oriented search through ontology-based sematic annotations - integration of knowledge and business processes - graphical user interfaces for retrieving and visualizing knowledge e. Developing new knowledge - innovation management - ontology learning and development - knowledge mining (from data, text and the Web) f. Measurement - measuring the benefits of knowledge management solutions - benchmarking - intellectual capital IMPORTANT DATES: - Submission of papers by August, 2, 2004 - Acceptance notices mailed by September, 20, 2004 - Final, camera-ready papers due by October, 25, 2004 CONTACT AND FURTHER INFORMATION: Prof. Dr. Dimitris Karagiannis Elena-Teodora Miron University of Vienna Institute for Computer Science and Business Informatics Department of Knowledge Engineering Br=FCnner Str. 72 1210 Vienna, Austria Phone: +43-(0)1-4277-38481 Fax: +43-(0)1-4277-38484 E-Mail: [EMAIL PROTECTED] www.dke.univie.ac.at/pakm2004 ------------------------------ From: "=?iso-8859-1?B?TWFya28gTeRraXDk5A==?=" <[EMAIL PROTECTED]> Subject: Mass Customization and Personalization Forum 2004 Date: Mon, 15 Mar 2004 16:31:54 +0200 CALL FOR PAPERS Mass Customization and Personalization Forum 2004 Implications to Management of Information Systems (Side event of ECIS 2004) THEME Information and Communication Technology (ICT) will play increasing and essential strategic role in the present business environment. ICT offer companies new ways to do business and new, emerging business strategies require more and more from ICT. One of the emerging business strategies is mass customization (MC), that is, ability to use flexible processes and organizational structures to produce varied and often individually customized products and services at the price of standardized, mass-produced alternatives. MC influences all industries from metal and electronic industries through fashion industry to software industry and everything between. Competitiveness in this environment demands the integration of ICT potential with these new business strategies. The theme of the workshop is 'Implications to Management of Information Systems'. This theme brings into attention the IS perspective to mass customization research, where information and knowledge as well as their processing are emphasized. Researchers and practitioners from different fields and different countries are invited to contribute to this multi-discipline forum on Mass Customization. LOCATION MCPF 2004 will be held in Turku School of Economics and Business Admistration. Premises are located almost in city center. Turku is the oldest city in Finland. The first record of the City of Turku is in a Papal decree dated on the 23rd of January 1229. The City houses over 170,000 people and the greater regional area about 300,000. Turku, with it's surroundings, is the fifth largest city in Finland and, along with Helsinki and Tampere, it is among the most significant regional areas in the country. The Turku area is well known especially for its enchanting archipelago, top ranking food and pharmaceutical companies. Turku also invests especially in biotechnology. Turku has excellent connections from the surrounding Europe. There are several direct daily flights from Stockholm, which take about 40 minutes, and from Helsinki, which take about 35 minutes. Train connections from Helsinki to Turku are available about once in hour and take about one hour. CALL FOR PAPERS Researchers and practitioners from different fields and different countries are invited to contribute to this multi-discipline forum on Mass Customization. Please submit a 1-3 page extended abstract for review by March 31, 2004. In your abstract you shoud define as clearly as possible the empirical or conceptual leap forward you are seeking, your methods, and the nature of your data. Abstracts will be reviewed by an international review board. Full paper is due to 30 April 2004. Important dates: March 2004 Deadline for submission of the extended abstracts March 2004 Notification on acceptance 30 April 2004 Deadline for submission of the full papers 30 April 2004 Early registration deadline 12-13 June 2004 MCP Forum 2004 For more detailed instructions, please look for: www.fimcp.fi/forum/submission.php For additional information, please contact organizers, [EMAIL PROTECTED] ------------------------------ From: "Dianhui Wang" <[EMAIL PROTECTED]> Subject: AI-2004: 17th Australian Joint Conference on Artificial Intelligence Date: Tue, 16 Mar 2004 16:43:29 +1100 AI-2004 First Call for Papers The 17th Australian Joint Conference on Artificial Intelligence in conjunction with the 7th Asia-Pacific Complex Systems Conference, Cairns Convention Centre, Queensland, Australia, 6th-10th December 2004 URL: http://ai2004.cqu.edu.au AI-2004 will be the 17th ACS Joint Conference on Artificial Intelligence. This series of conferences attracts leading researchers and practitioners from both Australia and overseas. The conference focuses on all aspects of artificial intelligence, from theoretical advances to the latest applied developments and, as such is of interest to both researchers and practitioners. AI-2004 invites authors to submit their original and unpublished work demonstrating current research in any area of Artificial Intelligence. IMPORTANT DATES Submission Date: 1st July 2004 Acceptance Date: 15th August 2004 Final Submission Date: 15th September 2004 Paper Submission and Instructions for authors Authors are invited to submit their complete manuscript in PDF format online [http://ai2004.cqu.edu.au]. As in previous years, the conference expects to publish the proceedings in the Springer Lecture Notes in Artificial Intelligence (LNAI) series. The length of submitted papers (excluding the title page) must be no more than 12 single-spaced, single-column pages including all figures, tables, and bibliography. Instructions for preparing the manuscript can be found at http://www.springer.de/comp/lncs/authors.html. Papers not conforming to the above requirements may be rejected without review. All papers will be peer reviewed by three members of the international programme committee. Special Sessions and Workshop/Tutorial AI-2004 solicits Special Session and Workshop/tutorial proposals. Please send proposals to [EMAIL PROTECTED] Special sessions are intended to usher in in-depth discussions in specialist areas relevant to the conference theme. The session organisers will coordinate the associated review process and conference proceedings will include all papers from the Special Sessions. To be placed on an email list for further information, please email the secretariat. For further details, please contact: AI-2004 Conference Secretariat Faculty of Informatics and Communication Central Queensland University Rockhampton Queensland 4702 Australia Tel: +61 749232145 Fax: +61 749309729 Email: [EMAIL PROTECTED] ------------------------------ From: Andrea Chiba <[EMAIL PROTECTED]> Subject: ICDL 04: 3rd Int'l Conf. on Development and Learning Date: Sat, 20 Mar 2004 02:23:58 -0800 (PST) ICDL 2004 FIRST CALL FOR PAPERS SUBMISSION DEADLINE: May 5 2004. THIRD INTERNATIONAL CONFERENCE ON DEVELOPMENT AND LEARNING: DEVELOPING SOCIAL BRAINS The Salk Institute October 20-22, 2004 San Diego, California http://icdl.cc The goal of the conference is to bring together leading researchers in neuroscience, machine learning, robotics, and developmental psychology, in order to gain new insights about learning and development in natural organisms and robots. The scope of developmental processes to be considered is broad, including cognitive, social, emotional, and many other skills exhibited by humans, and other animals. The theme of the conference this year will be "Developing Social Brains", but other topics related to development and learning are welcome. PAPER SUBMISSION Submission deadline is May 5 2004. Papers for the meeting can be submitted ONLY through the conference's web site at: http://icdl.cc. Papers can be submitted either as a 200 word summary or as a full paper (max 8 typeset pages). SPECIAL ISSUE ON NEUROCOMPUTING Authors of selected papers will be invited to submit an extended version of their paper for publication in a special issue of the Neurocomputing Journal, published by Elsevier Science B.V. (http://www.elsevier.nl/locate/neucom) REVIEW PROCESS All submitted papers will be reviewed by the program committee. Papers will be judged and accepted for the meeting based on the clarity with which the work is described and the relevance to the goals of the conference. All accepted papers not selected for oral talks as well as papers explicitly submitted as poster presentations will be included in one of three evening poster sessions. Authors will be notified of the presentation format of their papers by the beginning of July. For more information, visit http://icdl.cc ------------------------------ From: Robert Laurini <[EMAIL PROTECTED]> Subject: 24th Urban Data Management Symposium Date: Mon, 22 Mar 2004 12:50:53 +0100 UDMS 2004 24TH URBAN DATA MANAGEMENT SYMPOSIUM October 27-29, 2004 CHIOGGIA, VENICE, ITALY UDMS, the Urban Data Management Society, has organised international symposia at various locations in Europe in order to promote the development of information systems in local government since 1971. An important aim of UDMS has been to provide a forum for people to discuss new approaches, to consider new technologies and to share practical experiences in the field of urban data management. The focus has been on urban applications but regional and rural issues have always been well represented and have grown recently in importance. For the next symposium in Chioggia (near Venice, Italy), the organising committee invites you to submit a paper concerning the topics listed below. Theme 1): Nature, Collection Exchange, Use and Maintenance of Urban Data Topics: - Applications of high resolution remote sensing data - The new era of cartography and maps: their transformation to geographic/cartographic databases and the impact on many areas - Integration of data from multiple sources (for example public agencies/city authorities, etc.) and issues of scale, terminology/ontology structure, formats, etc. - Field data collection and quality control of urban data - Underground urban assets: the way to collect, store & visualize location, construction and condition data - Data availability and transparency issues - barriers to decision making - Data interchange Theme 2): Spatial Data Infrastructures Topics: - Spatial Data Infrastructures, especially at the regional and local level - Data Infrastructures for urban Location Based Services Theme 3): E-Governance Topics: - Spatially-enabled e-governance - GIS components of e-Government Theme 4): Applications Topics: - Disaster and Risk Management - Real time GIS, especially for environmental monitoring and control - Location based computing and services - Intelligent Transportation Systems - Temporal GIS Theme 5): Modelling Topics: - Three dimensional urban data modelling - Agent-based urban models Theme 6): Web-based and participatory systems Topics: - Community engagement: participation in gathering and using data; benefits and problems; accessibility and relevance of data at the community level - Public Participation GIS Theme 7): Urban Systems Technology Topics: - Local government enterprisedatabase with the capability for storing, accessing and manipulating spatial data, the exploitation of these capabilities in a web environment - The use of open source software in local government All accepted papers will be published and distributed to all participants at the symposium. IMPORTANT DATES: Abstract submission deadline: April 30, 2004 Notification of acceptance: May 31, 2004 Paper delivered by: July 31, 2001 UDMS 2004 dates: October 27-29, 2004 SUBMISSION: People interested to submit a paper for the event, are asked to deliver an abstract of at least 1000 words with reference to the theme/topic and a short Curriculum Vitae via our website www.udms.net following the instruction provided or by e-mail as attached files in Word-format, to the UDMS Executive Secretary Mrs Elfriede M. Fendel, e-mail [EMAIL PROTECTED], by April 30, 2004. Papers should be written and presented in English. All information concerning UDMS 2004 will be available at the UDMS web site: http://www.udms.net. For further information: UDMS Executive Secretary Mrs. Elfriede M. Fendel Section GIS technology OTB Research Institute for Housing, Urban and Mobility Studies Delft University of Technology Jaffalaan 9 NL-2628 BX Delft The Netherlands e-mail [EMAIL PROTECTED] ------------------------------ From: Mike Barley <[EMAIL PROTECTED]> Subject: SASEMAS 2004: CFP Date: Tue, 23 Mar 2004 21:19:38 +1200 1st INTERNATIONAL WORKSHOP ON SAFETY AND SECURITY IN MULTI-AGENT SYSTEMS (www.cs.auckland.ac.nz/research/safeagent/2004) Sponsored by THE BOEING CORPORATION to be held at the 3rd International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS) (satchmo.cs.columbia.edu/aamas04/) New York, USA 20 July 2004 IMPORTANT DATES: Paper Submission: April 1st 2004 Notifications: May 1st 2004 Camera-ready copy: May 30th, 2004 Workshop: Tuesday July 20, 2004 OVERVIEW As agent technology begins to be deployed in applications where incorrect or inappropriate agent behaviour can have harmful effects ranging from embarrassment to financial cost to physical injury to humans, safety and security are two central issues. Multiagent systems are being designed for ever more demanding and possibly hostile environments. For example, NASA has proposed missions where multiagent systems, working in space or on other planets, will need to do their own reasoning about safety issues that concern not only themselves but also that of their mission. Likewise, industry is interested in agent systems that can search for new supply opportunities and engage in (semi-)automated negotiations over new supply contracts. These systems should be able to securely negotiate such arrangements and decide which credentials can be requested and which credentials may be disclosed. Such systems may encounter environments that are only partially understood and where they must learn for themselves which aspects of their environment are safe and which are dangerous. On one side agents should act "safely": they should be robust enough to to avoid damages due to unexpected events, or internal bugs in non critical parts of their architecture. On the other side they should act "securely": they should be robust enough to resist potentially harmful effects due to malicious behavior of other agents. This workshop aims to bring together researchers, academics, practitioners and students interested in ways of ensuring that agent behaviour is safe and secure. While intelligent software agents and multiagent systems can provide many advantages over conventional software systems, they are also usually much more complex. Software agents often integrate such activities as deliberately planning to achieve their goals, dynamically reacting to unanticipated obstacles and opportunities, communicating with other agents to share information and coordinate actions, and even learning from and/or adapting to their environments. Because agents are often situated in dynamic environments, these activities must be carried out in a timely manner. These aspects of agents make the process of verifying and validating the safety and security of these systems much more difficult than for conventional software systems. Hence, verifying reasonable behavior from the agent and from multi agent systems requires new and different techniques and perspectives. The process of verifying and validating the safety of these systems is often complicated by the systems being open to unknown agents. Little, if anything, might be known about these agents. We need to be able to structure the system to handle the situatin when these agents might have goals that are atagonistic to the overall system goals. Moreover, even is the system is not open to all agents, there may still be security concerns if different agents are under the administrative control of different entities (eg in multi-national space missions or orchestrated financial web services). INTENDED PARTICIPANTS This workshop will be of interest to researchers and developers of agent systems for a wide range of emerging applications. The workshop will also be of interest to those that might use agent technology in safety critical applications, since these are the people that must be convinced of the safety and the security of these systems. PROPOSED TOPICS This workshop will explore issues related to the development and deployment of "safe and secure agent and multiagent systems". Relevant topics include, but are not limited to: - Definitions of safety and security for single agents or entire systems. What does it mean for an agent to be "safe", or to be "secure" and to "behave appropriately"? How can answers to the above questions be lifted to multiagent systems? - Verification/validation of agent and multiagent systems. How can agents, working in complex, open systems, be shown to be "safe" or "secure"? Can a multiagent system, that is composed of "safe" agents, be itself "unsafe"? Can the composition of "secure" agents lead to a "unsecure" system? - User requirements. Some obvious ones are that the user is safe from his agent performing any "risky" actions, that the agent is "safe" (i.e., robust) in a given environment, and that the multiagent society is safe from its member agents performing "malicious" actions. - Design, mechanisms and deployment. Do old-style formal specification, declarative languages, and user-friendly interfaces have roles to play for agent building environments? What mechanisms can be used to ensure/improve the safety or security of an agent and/or multiagent system? - Autonomy and Autonomous Reasoning. How can agents reason about their own safety? E.g., determining the types and degrees of dangers inherent in different courses of action. How can adjustable autonomy be used to ensure agents behave reasonably? - Learning/adaptive agents. How can agents that are self-modifying be shown to be safe and to avoid security related risks? In hostile environments, how can agents learn what is safe and secure to do and what is not? - Application areas. Which application areas would most benefit from agent technology but would also be very sensitive to safety or security issues? For further details, visit www.cs.auckland.ac.nz/research/safeagent/2004 ------------------------------ From: Franz Rothlauf <[EMAIL PROTECTED]> Subject: IEEE TEC: Special Issue on Analysis and Design of Representations Date: Thu, 25 Mar 2004 11:36:37 +0100 IEEE Transactions on Evolutionary Computation Special Issue on Analysis and Design of Representations and Operators http://www.cs.uu.nl/~dirk/adoro/cfp.html CALL FOR PAPERS Successful and efficient use of evolutionary algorithms (EAs) depends on the choice of the problem representation and the variation operators. These choices cannot be made independently of each other. The question whether a certain representation leads to better performing EAs than an alternative representation, can only be answered when the operators applied are taken into consideration. The reverse is also true: deciding between alternative operators is only meaningful in the context of a given representation. Clearly, this choice is problem-dependent, but despite the importance of choosing proper representation-operator combinations on the performance of EAs, little general applicable theory and knowledge is available to help understanding and guiding the construction of high-quality representations and operators for solving problems successfully and efficiently with EAs. The aim of the special issue is to provide a clear view of the state-of-the-art in the analysis and design of representations and operators. We are therefore soliciting papers that discuss the influence and importance of a proper choice of representations and operators for EA design, ranging from theoretical analysis to relevant and interesting real-life applications. TOPICS: - Theoretical and empirical properties of representations and/or operators - Interference between representations and operators - Predictive performance measures for evaluating representation and operator choices - Practical guidelines to design representation/operator combinations for a particular problem - Redundant versus non-redundant problem representations - High-locality versus low-locality representations - Search space bias of representations and operators IMPORTANT DATES - Submission deadline: November 30, 2004 - Notification of acceptance: February 28, 2005 - Delivery of final version: July 31, 2005 - Expected publication: February, 2006 FURTHER INFORMATION AND AUTHOR INSTRUCTIONS http://www.cs.uu.nl/~dirk/adoro/cfp.html ------------------------------ From: Eugene Eberbach <[EMAIL PROTECTED]> Subject: CEC 2004 Contests Date: Mon, 08 Mar 2004 17:07:58 -0500 CEC 2004 Contests There is still time to participate in the CEC 2004 Contests! Deadlines for entering are: Plant Competition May 15 2004 Binary Series Prediction Competition May 22 2004 Prisoner's Dilemma May 15th 2004 Car Racing April 30th 2004 Evolved Art May 29 2004 Visit the competition's page at http://www.cec2004.org/contests.htm for descriptions of the contests and contact people who will answer your questions. Some of our contests are specially designed to be easy to enter, others will be refereed by your colleagues at the conference. You must attend the conference to win so please remember to register. Preparing entries may take time so check the pages soon. Dan Ashlock, Contests Chair CEC 2004 ------------------------------ From: Jiri Ocenasek <[EMAIL PROTECTED]> Subject: Deadline Extended: GECCO Workshop on Adaptation, Approximation, ... Date: Tue, 9 Mar 2004 18:06:40 +0100 (MET) The deadline for the GECCO-2004 workshop on Adaptation, Approximation, and Learning in Evolutionary Computation is now extended. We heartily invite your submissions. More information can be found at http://www.inf.ethz.ch/personal/jirio/GECCO-2004/ IMPORTANT DATES (updated): April 4 Paper submission (from 4 to 10 pages, only PDF accepted). Please send your paper to Jiri Ocenasek ([EMAIL PROTECTED]). April 19 Notification of paper acceptance/rejection. April 28 Camera ready paper (only PDF accepted). June 27 Workshop in Seattle. ------------------------------ From: "Ivan Garibay" <[EMAIL PROTECTED]> Subject: Deadline Extended: GECCO Workshop on Self-organization in ... Date: Fri, 12 Mar 2004 15:27:51 -0500 WORKSHOP ON Self-organization in Representations for Evolutionary Algorithms: Building complexity from simplicity http://ivan.research.ucf.edu/SOEA.htm * Papers submission deadline EXTENDED: April 16, 2004 * Important Dates Papers Due: April 16, 2004 (April 28 for one-page position statements) Acceptance notices: April 19, 2004 Camera Ready: April 28, 2004 Workshop: June 27, 2004 ------------------------------ From: Wiebe van der Hoek <[EMAIL PROTECTED]> Subject: Deadline Extended: LOFT6 Date: Thu, 18 Mar 2004 12:27:16 +0000 (GMT) The deadline for submission of papers to be presented at the LOFT6 conference (Sixth conference on Logic and the Foundations of Game and Decision Theory, Leipzig, Germany, July 16-18) is March 31, 2004 For information on the submission procedure and general information about the conference click the following link: http://www.econ.ucdavis.edu/faculty/bonanno/loft6_call.html ------------------------------ From: Johannes Fuernkranz <[EMAIL PROTECTED]> Subject: ICML-04 Tutorial and Workshop Program Date: Thu, 18 Mar 2004 15:11:24 +0100 The 21st International Conference On Machine Learning (ICML-04) July 4-8, 2004, Banff, Alberta, Canada Tutorial and Workshop Program The following workshops and tutorials will be held at the 21st International Conference on Machine Learning: TUTORIALS Morning Tutorials * M1: The Many Faces of ROC Analysis in Machine Learning o Peter Flach (University of Bristol) * M2: Bayesian Methods for Machine Learning o Zoubin Ghahramani (University College London) * M3: Spectral Clustering o Chris Ding (Lawrence Berkeley National Laboratory) * M4: Game-theoretic Learning o Amy Greenwald (Brown University) Afternoon Tutorials * A1: Junk E-mail Filtering o Geoff Hulten (Microsoft Research) o Joshua Goodman (Microsoft Resarch) * A2: Kernels for Structured Data o Thomas Gärtner (Fraunhofer Institut AIS) * A3: Probabilistic Logic Learning o James Cussens (University of York) o Kristian Kersting (Albert-Ludwigs University of Freiburg) * A4: Data Structures for Fast Statistics o Alexander Gray (Carnegie Mellon University) o Andrew Moore (Carnegie Mellon University) The tutorials will be held on the first day of the conference, July 4th, 2004. Tutorial fees are included in the ICML registration, but they can also be attended independent of the conference. More details can be found at http://www.oefai.at/icml-04/tutorials.html WORKSHOPS * Predictive Representations of World Knowledge Organizers: o Rich Sutton (University of Alberta) o Satinder Singh (University of Michigan) * Relational Reinforcement Learning Organizers: o Prasad Tadepalli (Oregon State University) o Robert Givan (Purdue University) o Kurt Driessens (Catholic University of Leuven) * Statistical Relational Learning Organizers: o Tom Dietterich (Oregon State University) o Lise Getoor (University of Maryland) o Kevin Murphy (MIT) * Physiological Data Modeling - A Competition Organizers: o David Andre (Bodymedia, Inc.) o Peter Stone (University of Texas, Austin) The first three workshops will have the following joint paper submission deadlines. Apr 2, 2004 WS Paper submission deadline Apr 16, 2004 Notification of participants May 7, 2004 WS final paper deadline The workshops will be held on July 8th, the last day of the conference. Workshop fees are not included in the regular conference fees. The workshops can also be attended independent of the main conference. More details can be found at http://www.oefai.at/icml-04/workshops.html. ------------------------------ From: Gianluca Bontempi <[EMAIL PROTECTED]> Subject: Career Opportunities Date: Mon, 08 Mar 2004 17:50:51 +0100 Open position for a professor at the Department of Computer Science of ULB (Free University of Brussels) The Faculty of Sciences of the Free University of Brussels (ULB) announces the opening of a full-time position for a "chargé de cours" (first professorial level) in Computer Science, starting October the 1st, 2004. This is a tenured full-time permanent position within the Computer Science Department. The position involves both teaching and research and some commitment to administrative tasks. For candidates not fluent in French, a temporary period of teaching in English may be granted. Preference is given to candidates able to reinforce one of the existing groups of the Computer Science Department, in one of the following areas: · Algorithms · Combinatorial Optimization · Stochastic modeling and machine-learning methods Full details available at http://www.ulb.ac.be/di/Vacances/vacance_CC_2004_en.html ------------------------------ From: [EMAIL PROTECTED] (Arun Sharma) Subject: Program Leader: Symbolic Machine Learning and Knowledge Acquisition Date: Mon, 15 Mar 2004 15:07:21 +1100 NATIONAL ICT AUSTRALIA LIMITED Australia's New Centre of ICT Excellence PROGRAM LEADER, SYMBOLIC MACHINE LEARNING and KNOWLEDGE ACQUISITION National ICT Australia (NICTA) is seeking an outstanding Research Program Leader to provide inspirational leadership for a Program in Symbolic Machine Learning and Knowledge Acquisition at its Sydney Research Laboratory. The Program concentrates on symbolic approaches to research in machine learning and knowledge acquisition and is motivated by the need to make sense out of the explosion in data and device complexity. The program currently has a strong group of early career researchers in robotics and learning and has participation from the machine learning and knowledge acquisition researchers in the School of Computer Science and Engineering at the University of New South Wales. The Program Leader will be expected to build on the current strengths and broaden the research profile of the program. The Program Leader will be responsible for: * Providing research leadership for the Program; * Contributing to the development of research priorities, research training, supervision of PhD students, and collaborative project formation; * Attracting and hiring research staff for the program; * Building linkages to other institutions, industry (both Australian and international), relevant government agencies and promoting commercialisation activities. Further information, which details the information required from all applicants, is available on the NICTA website (http://www.nicta.com.au). You may direct queries to: Professor Arun Sharma Director, Sydney Research Laboratory National ICT Australia Limited Email [EMAIL PROTECTED] Phone: +61 2 9385 7334 Applications for this position should be submitted to [EMAIL PROTECTED] by 15 April 2004. ------------------------------ From: "Joseph Haley" <[EMAIL PROTECTED]> Subject: Open Position---Fulltime Scientific Software Engineer Date: Wed, 24 Mar 2004 17:51:54 -0500 Job title: Senior Scientist Req. no. 0013 No. Positions: 1 Type: Full Time Updated: March 24 2004 Responsibilities: Seeking a senior computer scientist or computational linguist with expertise in machine learning and natural language processing to join a team of researchers and engineers developing innovative technology in speech understanding. Required Skills, Experience & Education: Preferred Experience: * M.S. or Ph.D. in Computer Science, Computational Linguistics or related field. * Solid industry experience writing production code in C/C++ and/or Java. * In-depth knowledge of machine learning techniques as applied to natural language processing. * Support vector machines. * Speech recognition and synthesis. * XML. * Telephony For more details, please contact: Joseph P Haley President Corsair Solutions, Inc 29 Water St Suite 216 Newburyport,MA 01950 www.corsairsolutions.com Phone: 978-465-0085 FAX: 978-465-0068 Cell: 978-430-1333 ------------------------------ From: Raul Valdes-Perez <[EMAIL PROTECTED]> Subject: automatic clustering of all 702 MLJ articles Date: Fri, 12 Mar 2004 17:09:30 -0500 Greetings, here is an automatic clustering of all MLJ articles ever published; 702 articles in total: http://vivisimo.com/mlj You can get alternative clusterings by clicking on the tabs: - Keys (keywords) - Who (authors) - Where (affiliation/address) You can enter an author or concept in the middle-left (Find in Clusters) and see highlighted matches in the clusters, for some easy ego-searching or people-checking. This clustering, done in collaboration with Kluwer, is a parting gift as I ended my service as MLJ editor. Raul Valdes-Perez President, Vivisimo Inc. Adjunct Assoc Prof, CMU Comp Sci ------------------------------ From: Wiebe van der Hoek <[EMAIL PROTECTED]> Subject: 6th European Agent Systems Summer School: CFP Date: Thu, 18 Mar 2004 12:23:37 +0000 (GMT) After successful summer schools on Agent Systems in Utrecht, Saarbrucken, Prague, Bologna and Barcelona, AgentLink III organises the 6th European Agent Systems Summer School Liverpool, UK, 5 - 9 July 2004. EASSS 2004 will consist of a mixture of introductory and advanced courses delivered by internationally leading experts in the agent field, and will cover the full range of theoretical and practical aspects of agent-based computing. EASSS'04 is open to anyone from research or industry, both AgentLink members and non-members alike. A registration fee will be charged to cover costs, but some support will also be available for PhD students. There are several cheap connections from European cities to Liverpool, and convenient intercontinental flights to London or Manchester. For more information and registration: http://www.agentlink.org/happenings/easss/2004/index.html ------------------------------ From: Professor Ron Sun <[EMAIL PROTECTED]> Subject: New issues of cognitive systems research Date: Wed, 24 Mar 2004 17:51:19 -0500 New issues of COGSYS are now available: Cognitive Systems Research Volume 5, Issue 1, Pages 1-92 (March 2004) http://www.sciencedirect.com/science/issue/6595-2004-999949998-477744 Cognitive Systems Research Volume 5, Issue 1, Pages 1-92 (March 2004) TABLE OF CONTENTS Measurement and the explanation of adaptive and novel behaviors in real and artificial creatures, Pages 3-39 Tony Savage http://www.sciencedirect.com/science/article/B6W6C-49Y98GB-1/1/377a64b17e66f20cb54bdfa975817109 Collaborative discovery in a simple reasoning task, Pages 41-62 Kazuhisa Miwa http://www.sciencedirect.com/science/article/B6W6C-4B4PS1K-1/1/91f1ee47d880d80b96a20d3d30a74a68 Top-down versus bottom-up learning in cognitive skill acquisition, Pages 63-89 Ron Sun and Xi Zhang http://www.sciencedirect.com/science/article/B6W6C-4B4XNFS-1/1/7355a40f04b5fec0d36494e2d947db08 Cognitive Systems Research Volume 5, Issue 2, Pages 93-168 (June 2004) http://www.sciencedirect.com/science/issue/6595-2004-999949997-489549 Cognitive Systems Research Volume 5, Issue 2, Pages 93-168 (June 2004) TABLE OF CONTENTS Neural coding strategies and mechanisms of competition, Pages 93-117 M. W. Spratling and M. H. Johnson http://www.sciencedirect.com/science/article/B6W6C-4B8K8K1-1/1/ed991cedac96d6afcf0fbd5177af09bf A symbolic model of human attentional networks, Pages 119-134 Hongbin Wang , Jin Fan and Todd R. Johnson http://www.sciencedirect.com/science/article/B6W6C-4BMC5RR-1/1/586352b2e5ee4da2711b2655f3114b87 Cognitive paradigms: which one is the best?, Pages 135-156 Carlos Gershenson http://www.sciencedirect.com/science/article/B6W6C-4B4PS1K-2/1/6f37de20de6e2aa94ee0c30a6b19867c Review of Pointing: Where Language, Culture and Cognition Meet, S. Kita (Ed.); Lawrence Erlbaum Associates, 2003; ISBN 0-8058-4014-1, Pages 157-165 David A. Leavens http://www.sciencedirect.com/science/article/B6W6C-4BMC5RR-2/1/3e6f9639425654d46a7da63c262faf6d If you have questions, please locate Help Desk at http://www.info.sciencedirect.com/contacts. See the following Web page for submission, subscription, and other information regarding Cognitive Systems Research: http://www.cogsci.rpi.edu/~rsun/journal.html ------------------------------ End of ML-LIST Digest Vol 16, No. 6 ************************************