Machine Learning List: Vol. 15, No. 2 Monday, Jan 20, 2003 Contents Calls for Papers and Other Meeting Announcements CFP: ICML'03 (International Conference on Machine Learning) CFP: Int Conf on Machine Learning and Applications, ICMLA'03 Call for papers: Discovery Science (DS'03) CfP IJCAI '03 - 3rd Workshop on Creative Systems IEEE/WIC Intelligent Agent Technology 2003: Call For Papers Call for Papers: KI2003 ACL2003 CFP: Wrkshp on Multilingual Summarization & Quest Answering CFP: Learning Graphical Models for Comp Genomics (IJCAI03 Wrkshp) Wrkshp on Advances in Machine Learning, Montreal, June 2-6, 2003 Career Opportunities Faculty position at NYU PostDoc vacancy - Marie Curie fellowship Misc Other Announcements jmlr-announce: ICML Special Issue The Machine Learning List is moderated. Contributions should be relevant to the scientific study of machine learning. Please send submissions for distribution to: ml@isle.org. For requests to be added, removed, or to change your email address, send email to: ml-request@isle.org. In general, submissions should be no more than a few full-screens of text. For meeting announcements, highlight the conference or workshop web page and give a summary description of the goals of the event. Information such as the list of program committee members, talk schedules, and registration forms are unnecessary and should not be included. Job adds are usually no more than a few full-screens so they should fit naturally. ---------------------------------------------------------------------- From: Nina Mishra Subject: CFP: ICML'03 (International Conference on Machine Learning) Date: Wed, 15 Jan 2003 18:58:58 -0800 Call for Papers The Twentieth International Conference on Machine Learning Washington, DC USA August 21-24, 2003 The Twentieth International Conference on Machine Learning (ICML-2003) will be held in Washington D.C. August 21-24, 2003. The conference will bring together researchers to exchange ideas and report recent progress in the field of machine learning. TOPICS FOR SUBMISSION ICML-2003 welcomes submissions on all topics related to machine learning. We specifically encourage papers on the following topics: - Applications of machine learning, particularly those that require non-standard techniques or shed light on limitations of existing techniques. - The role of learning in design and configuration, logical and spatial reasoning, motor control, and more generally on learning for performance tasks carried out by intelligent agents. - The discovery of scientific laws and taxonomies, the construction of componential and structural models, and learning at multiple levels of temporal and spatial resolution. - Computational models of human learning, exploratory research that describes novel learning tasks, work that integrates familiar methods to demonstrate new functionality, and agent architectures in which learning plays a central role. - The effect of the developers' decisions about problem formulation, representation, data quality, and reward function on the learning process. - Empirical studies that combine natural data (to show relevance) with synthetic data (to understand conditions on behavior), along with formal analyses that make contact with empirical results, especially where the aim is to identify sources of power, rather than to show one method is superior to others. We also welcome submissions from all traditional topics of machine learning. Submissions that demonstrate both theoretical and empirical rigor are especially encouraged. The conference will be co-located with KDD-2003 and COLT-2003. Details of the co-location will be announced shortly. IMPORTANT DATES Abstracts due: February 10, 2003 Submissions due: February 14, 2003 Acceptance decisions mailed to authors: April 25, 2003 Camera-ready copies of all accepted papers due: May 16, 2003 Authors of conditionally accepted papers notified: May 23, 2003 ADDITIONAL INFORMATION For additional information, please see the conference web site: http://www.hpl.hp.com/conferences/icml2003 which will provide additional details as they become available. ------------------------------ From: "Krzysztof (Krys) Cios" Subject: CFP: Int Conf on Machine Learning and Applications, ICMLA'03 Date: Sat, 04 Jan 2003 16:18:12 -0800 Could you please announce this link to the International Conference on Machine Learning and Applications, ICMLA'03, that I am organizing? http://www.cs.csubak.edu/~icmla/icmla03/icmla03.html Krzysztof (Krys) Cios Professor and Chair Computer Science and Engineering Department at CU Denver ------------------------------ From: Gunter Grieser Subject: Call for papers: Discovery Science (DS'03) Date: Mon, 6 Jan 2003 18:24:23 +0100 Call for Papers: Discovery Science 2003 The 6th International Conference on Discovery Science (DS03) Hokkaido University, Sapporo, Japan October 17-19, 2003 www.intellektik.informatik.tu-darmstadt.de/DS03/ GENERAL INFORMATION: The 6th International Conference on Discovery Science (DS 2003) will be held at the Hokkaido University, Sapporo, Japan, during October 17-19, 2003. DS 2003 will be co- located with the 14th International Conference on Algorithmic Learning Theory. The two conferences will be held in parallel, and they will share their invited talks. We are now encountered to a rapidly growing digital network society. Information available for each person is tremendously large and therefore is far beyond our capability for analyzing and understanding. A new generation of computational techniques and tools is required to support the extraction and the discovery of useful knowledge from the rapidly growing volumes of data. Raw data is rarely of direct benefit. Its true value is reflected by our ability to extract information useful for decision support or for exploration and understanding of the phenomena exhibited in the data source. The main objective of DS 2003 is to provide an open forum for intensive discussions and interchange of new information among researchers working in the area of Discovery Science. IMPORTANT DATES: Submission Deadline: April 12, 2003 Notification of Acceptance June 1, 2003 Camera-ready Due July 1, 2003 Conference October 17-19, 2003 TOPICS OF INTEREST: We invite submissions from (but not limited to) the following areas: logic for/of knowledge discovery; knowledge discovery by inferences; abductive reasoning; heuristic search; constructive programming as discovery; knowledge discovery from texts and the Web; knowledge discovery from unstructured and multimedia data; knowledge discovery in databases; data mining; data and knowledge visualization; active mining; knowledge discovery in network environments; intelligent network agents; machine learning; statistical methods and neural networks for knowledge discovery; Bayesian networks; knowledge discovery and human interaction; human factors in knowledge discovery; philosophy and psychology of discovery; chance discovery; scientific discovery; application of knowledge discovery to natural and social sciences. CONFERENCE HOMEPAGE: www.intellektik.informatik.tu-darmstadt.de/DS03/ ------------------------------ From: Sender: "Carlos Lisboa Bento" To: Subject: CfP IJCAI '03 - 3rd Workshop on Creative Systems Date: Tue, 7 Jan 2003 17:43:35 -0000 CALL FOR PAPERS 3rd. WORKSHOP ON CREATIVE SYSTEMS Approaches to Creativity in Artificial Intelligence and Cognitive Science 18th International Joint Conference on Artificial Intelligence (IJCAI 2003) Acapulco, Mexico, 10-11 August 2003 Submission deadline: March 21, 2003 website: http://creative-systems.dei.uc.pt/CSW-IJCAI03/ The Program Committee of the 3rd Workshop on Creative Systems - Approaches to Creativity in Artificial Intelligence and Cognitive Science - invites submissions of technical and position papers for the workshop. The workshop will be held at Acapulco, Mexico, on 10-11 August 2003, as part of the 18th International Joint Conference on Artificial Intelligence (IJCAI 2003). The publication of the Proceedings of the Workshop is being negotiated with a publisher. WORKSHOP OBJECTIVES This workshop will bring together researchers from AI and Cognitive Science working on Creative Systems, 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 - Computational tools for supporting Creativity - Applications of Creative Systems IMPORTANT DATES March 21, 2003 Submission deadline April 11, 2003 Notice of Acceptance May 23, 2003 Deadline for final camera-ready copies WORKSHOP WEB SITE http://creative-systems.dei.uc.pt/CSW-IJCAI03/ ------------------------------ From: "jxl" Subject: IEEE/WIC Intelligent Agent Technology 2003: Call For Papers Date: Tue, 7 Jan 2003 20:59:46 -0800 IEEE/WIC Intelligent Agent Technology 2003 C A L L F O R P A P E R S 2003 IEEE/WIC International Conference on Intelligent Agent Technology (IAT 2003) Sponsored by IEEE Computer Society and Web Intelligence Consortium (WIC) October 13-17, 2003 Tianlun Dynasty Hotel, BEIJING, CHINA Homepage: http://www.comp.hkbu.edu.hk/IAT03 The 2003 IEEE/WIC International Conference on Intelligent Agent Technology (IAT 2003) will be jointly held with the 2003 IEEE/WIC International Conference on Web Intelligence (WI 2003 http://www.comp.hkbu.edu.hk/WI03/). The IEEE/WIC 2003 joint conferences are sponsored and organized by IEEE Computer Society Technical Committee on Computational Intelligence (TCCI) (http://www.cs.uvm.edu/%7Exwu/tfvi/index.shtml) and by Web Intelligence Consortium (WIC) (http://wi-consortium.org). The upcoming meeting in this conference series follows the great success of IAT-99 held in Hong Kong in 1999 and IAT-01 held in Maebashi City, Japan in 2001. TOPICS The topics and areas to be addressed include, but not limited to: Learning and Self-Adapting Agents Adaptation and self-adaptation Artificial life Behavioral selection Behavioral self-organization Believable lifelike quality Classifier systems Coordinating perception, thought, and action Evolution and learning in dynamic environments Evolutionary computation Integrated exploration and exploitation Uncertainty management in multi-agent systems Data and Knowledge Management Agents Adaptation and evolution of knowledge networks Data mining Distributed knowledge systems Heterogeneous data integration and management Human-agent interaction Information filtering Knowledge aggregation Knowledge discovery Knowledge sharing Reasoning and planning IMPORTANT DATES Electronic submission of full papers: March 20, 2003 (Research track and industry track) Notification of paper acceptance: May 2003 (Research track and industry track) Workshop and tutorial proposal submission: June 1, 2003 Camera-ready of accepted papers: June 2003 Notification of workshops and tutorials: July 2003 Conference & workshops: October 13-17, 2003 ------------------------------ From: Rudolf Kruse Subject: Call for Papers: KI2003 Date: Fri, 10 Jan 2003 15:04:12 +0100 (MET) * CALL FOR PAPERS * 26th German Conference on Artificial Intelligence (KI-2003) http://www.ki2003.de September 15-18, 2003 University of Hamburg, Germany The conference invites original research papers in all areas of AI. Besides papers on the foundations of AI we also welcome reports on innovative applications. TOPICS Possible Areas of interest include, but are not limited to: Agent Technology, Automated Reasoning, Case-Based Reasoning, Cognitive Modeling, Configuration and Diagnosis, Decision Support Systems, Image Understanding, Knowledge Discovery, Knowledge Management, Machine Learning, Multi Media, Natural Language Processing, Ontologies, Neural Networks, Planning and Scheduling, Reasoning under Uncertainty, Robotics, Semantic Web, Soft Computing, Temporal and Spatial Reasoning, Vision A special focus of the conference is on Multi Modality. Papers in this area are particularly welcome. IMPORTANT DATES Submission of electronic abstracts and papers: April 7, 2003 Notification for conference papers: June 2, 2003 Camera-Ready copies for conference papers: June 30, 2003 ------------------------------ From: Priscilla Rasmussen Subject: ACL2003 CFP: Wrkshp on Multilingual Summarization & Quest Answering Date: Fri, 10 Jan 2003 14:01:40 EST CALL FOR WORKSHOP PAPERS ACL 2003 Post-conference Workshop Sapporo Convention Center, Sapporo, Japan July 11-12, 2003 Workshop on "Multilingual Summarization and Question Answering - Machine Learning and Beyond" Automatic summarization and question answering aim at producing a concise, condensed representation of the key information content in an information source for a particular user and task. Interest in automatic summarization and question answering continues to grow, motivated by the explosion of on-line information sources and advances in natural language processing and information retrieval. In fact, various forms of automatic summarization and question answering will undoubtedly be indispensable given the massive information universes that lie ahead in the 21st century. Summarization and question answering involves the extraction or generation of text snippets to fulfill some user needs. Rule-based or statistical-based summarization and QA systems have shown promising results in the TREC QA-tracks, NTCIR QAC, and NIST DUC; it is, however, very difficult to find good evaluation functions or rules that work well across domains or in all questions because there are many system parameters that must be carefully tuned in order to achieve good system performance. In consequence, various machine learning (ML) techniques have recently been applied to summarization and QA systems. The purpose of this workshop is to provide a forum for exploring the commonality underling this diversity of problem domain and approaches. The workshop has the following goals: - to bring together communities of researchers who apply machine learning techniques to summarization and QA systems, - to deepen the summarization and QA community's understanding of the state of the art in machine learning, - to identify summarization and QA-related problems for which ML techniques might be appropriate, and - to advance the state of the art of summarization and QA technologies. Topics appropriate to this workshop include: - summarization or QA systems with ML techniques, - novel or improved ML techniques for summarization or QA, - effective feature extraction methods for characterizing summarization or QA, - metrics and benchmarks for evaluating the effect of machine learning techniques in summarization or QA systems, - generation for summarization or QA, - cross-language or multilingual QA, - integration with Web and IR access, - corpora creation for summarization or QA, - interfaces and tools for summarization or QA. DEADLINES (Tentative) Paper submission deadline: Apr 21, 2003 Notification of acceptance for papers: May 19, 2003 Camera ready papers due: May 26, 2003 Workshop date: July 11-12, 2003 ------------------------------ From: "Roby Joehanes" Subject: CFP: Learning Graphical Models for Comp Genomics (IJCAI03 Wrkshp) Date: Sat, 11 Jan 2003 18:08:16 -0600 Second CFP: IJCAI-2003 Workshop -- Learning Graphical Models for Computational Genomics Saturday, 9 August 2003 Acapulco, Mexico http://www.kddresearch.org/KDD/Workshops/IJCAI-2003-Bioinformatics/ Recent advances in experimental tools for computational genomics have led to sharp growth in data resources for bioinformatics problems such as modeling of gene expression and gene-protein interaction. This provides an interesting application domain for intelligent systems that learn graphical models from data for causal modeling, time series simulation and prediction, and classification and regression problems in computational life sciences. In response, we propose a workshop to bring together researchers in intelligent systems who are interested in: * probabilistic reasoning and learning with the primary focus of: - learning the structure of graphical models from data, - new graphical models such as types of dynamic Bayesian networks, stochastic and other approximation algorithms for inference, - structure learning; * constraint-based knowledge representation; * parameter estimation on graphical models and dynamical systems. TOPICS Active research topics that are relevant to learning graphical models for computational genomics include: * functional genomics, which includes: - modeling of gene regulatory dynamics, - data mining from DNA hybridization microarrays, - other gene modeling tools such as northern blots; * building simulation models for metabolomics on: - biochemical pathways, - environmental stress-response, - cellular process regulation; * proteomics, such as: - secondary and tertiary fold prediction - gene-protein interaction; * other contemporary bioinformatics problems, such as: - intelligent systems for pharmacology, - plant science and crop simulation, - decision support systems for human and veterinary medicine, - phylogenetic modeling. IMPORTANT DATES Mar 01, 2003 Submission deadline Mar 21, 2003 Acceptance notification May 16, 2003 Camera-ready version of papers ADDITIONAL INFORMATION Please consult the following web page: http://www.kddresearch.org/KDD/Workshops/IJCAI-2003-Bioinformatics/ for more information. ------------------------------ From: Balazs Kegl Subject: Wrkshp on Advances in Machine Learning, Montreal, June 2-6, 2003 Date: Mon, 13 Jan 2003 14:23:45 -0500 Call for papers Workshop on Advances in Machine Learning Montreal, Canada, June 2-6, 2003 URL: www.iro.umontreal.ca/~lisa/workshop2003.html ORGANIZERS: Yoshua Bengio, Balazs Kegl (University of Montreal) Doina Precup (McGill University) SCOPE: Probabilities are at the core of recent advances in the theory and practice of machine learning algorithms. The workshop will focus on three broad areas where these advances are crucial: statistical learning theory, learning algorithms, and reinforcement learning. The workshop will therefore bring together experts from each of these three important domains. Among the sub-topics that will be covered, we note: variational methods, graphical models, the curse of dimensionality, empirical methods to take advantage of theories of generalization error, and some of the applications of these new methods. On the theoretical side, in recent years a lot of effort has been devoted to explain the generalization abilities of popular learning algorithms such as voting classifiers and kernel methods. Some of these results have given rise to general principles that can guide practical classifier design. Some (non-exclusive) sub-topics in this aspect of the workshop include Rademacher and Gaussian complexities, algorithmic stability and generalization, localized complexities and results on the generalization ability of voting classifiers and kernel-based methods. On the algorithmic side, one of the emphasis of recent years has been on probabilistic models that attempt to capture the complex structure in the data, often by discovering the main lower-dimensional features that explain the data. This raises interesting and difficult questions on how to train such models, but such algorithms may have wide ranging applications in domains in which the data has interesting structure that may be explained at multiple levels, such as in vision and language. In reinforcement learning (RL), recent research has brought significant advances in some of the traditional problems, such as understanding the interplay between RL algorithms and function approximation, and extending RL beyond MDPs. At the same time, new areas of research, such as computational game theory, have developed at the interface between RL and probabilistic learning methods. In this workshop, we invite presentations on all RL topics, ranging from theoretical development to practical applications. IMPORTANT DATES: March 31, Paper submission deadline April 15, Notification of paper acceptance/rejection. ------------------------------ From: Foster Provost Subject: Faculty position at NYU Date: Tue, 07 Jan 2003 15:33:33 -0500 Asst/Assoc/Full Professor, Visitor or Tenure-Track in New York City The Information Systems Group within the Department of Information, Operations, & Management Sciences at NYU's Stern School of Business is interested in complementing its existing strengths, including its strong presence in the data mining and database communities, and its strong behavioral and economics faculty. Tenure-track: New York University's Stern School of Business invites applications for tenure-track faculty positions at all levels for the 2003-2004 academic year. A candidate should have a Ph.D. in Computer Science or be assured of its completion within one year, and is expected to be a productive researcher and effective teacher at undergraduate, MBA and PhD levels in the application of information technology to the solution of business problems, including how technology creates new capabilities or improved performance for businesses. An applicant should have strong research potential or established research record (depending on level), including publications in top-level journals and conference proceedings. Visiting faculty: Applications are solicited for full-time visiting positions at all levels. Visiting faculty teach at the undergraduate and/or MBA levels and are active in research in the department. Candidates must present evidence of strong teaching ability and research performance. http://www.stern.nyu.edu/is/ ------------------------------ From: "Filippo Neri" Subject: PostDoc vacancy - Marie Curie fellowship Date: Fri, 17 Jan 2003 16:47:09 +0100 MARIE CURIE FELLOWSHIP ANNOUNCEMENT Contract Number HPMI-CT-1999-00036 Core Project Title Data and knowledge management Job Description Natural Language Processing/Computational Linguistics in the UK Totally committed to scientific exploration and discovery, Unilever invests £550 million in pioneering new research so our products remain the preferred choice, 150 million times a day. An ideal opportunity for a recent PhD graduate to develop their career whilst keeping their options open on whether to work in industry or academia, we're looking for a postdoctoral fellow to join our 2-year Marie Curie Scheme. Delivering innovation and technology within a challenging environment, you'll be fully integrated within the various research groups and benefit from our comprehensive training and development opportunities offered to all scientists. One of these training programmes is a 2-year scientist development programme which is designed to develop business competencies. Our iConnect Group is seeking two imaginative researchers to work in one of the following areas of Language Engineering: text analysis, message understanding, text categorisation, topic detection / tracking, statistics for NLP, language generation, dialogue models and dialogue management, question answering, knowledge representation or other relevant areas of interest. A key member of the group, you will participate in the research and consultation with our business users, and in the design, the development and the implementation of Language Engineering solutions. You will also gain valuable network opportunities with our external academic links. In addition to the acquisition of valuable and sought-after transferable skills in the design and development of specialist language engineering systems, you'll receive a subsistence and mobility allowance. For further details visit: http://www.cordis.lu/improving/ http://www.cordis.lu/improving/fellowships/home.htm. Please note that usual European Union Marie Curie eligibility criteria apply. To apply, please send a full CV, together with the contact details of two referees to Shail Patel, Unilever Research, Quarry Road East, Bebington, Wirral CH63 3JW. E-mail: shail.patel@unilever.com Fellowship Level Postgraduate Number of Fellowships 2 Deadline 31/01/2003 Start Date 01/04/2003 Duration 24 months Salary 26k pounds per annum Supervisor MR Shail PATEL shail.patel@unilever.com http://www.unilever.com http://research.unilever.worldonline.nl ------------------------------ From: "David 'Pablo' Cohn" Subject: jmlr-announce: ICML Special Issue Date: 13 Jan 2003 10:06:53 -0800 The Journal of Machine Learning Research is very pleased to announce publication of a Special Issue of invited papers from the Eighteenth International Conference on Machine Learning (ICML2001). This issue, edited by Carla Brodley and Andrea Danyluk, contains twelve papers expanded from their ICML form into fully refereed JMLR contributions. We believe they capture both the breadth and spirit of the machine learning conference and community. The new issue is available online at http://www.jmlr.org. David Cohn Managing Editor, JMLR ------------------------------ End of ML-LIST Digest Vol 15, No. 2 ***********************************