Machine Learning List: Vol. 15, No. 11 Saturday, July 5, 2003 Contents Calls for Papers DATA STREAMS TRACK, ACM SAC 2004 MIR03 JASIST special issue on Computational Approaches to Style IEEE Int'l Conference one-Technology, e-Commerce and e-Service ECIR-04 26th European Conference on Information Retrieval IAS-8 Machine Learning as Experimental Philosophy of Science ITCLS 2003 - Deadline extended to July 14th, 2003 Career Opportunities Postdoctoral positions in Toronto Phd Studentships - School of Computing, RGU, Scotland Research Fellow positions at Univ. College London (Adastral Park) Miscellany Initial IBAL release 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 ads are usually no more than a few full-screens so they should fit naturally. ---------------------------------------------------------------------- From: "Jesus S. Aguilar" Subject: DATA STREAMS TRACK, ACM SAC 2004 Date: Sat, 21 Jun 2003 13:17:07 +0200 CALL FOR PAPERS: ACM SAC 2004, DATA STREAMS TRACK http://www.lsi.us.es/~aguilar/ds/ ACM SYMPOSIUM ON APPLIED COMPUTING, SAC 2004 March 14-17, 2004, Nicosia, Cyprus For the past eighteen years, the ACM Symposium on Applied Computing has been a primary gathering forum for applied computer scientists, computer engineers, software engineers, and application developers from around the world. SAC 2004 is sponsored by the ACM Special Interest Group on Applied Computing, and is hosted by the University of Cyprus in Nicosia, Cyprus. DATA STREAMS TRACK The rapid growth in information science and technology in general and the complexity and volume of data in particular have introduced new challenges for the research community. Databases are growing incessantly and, in many cases, we need to extract some sort of knowledge from this continuous stream of data. The goal of the track is to convene researchers who deal with decision rules, decision trees, association rules, clustering, filtering, pre-processing, post-processing, feature selection, visualization techniques, etc. from data streams. Topics include but are not restricted to: Data Stream Models Clustering from Data Streams Decision Trees from Data Streams Association Rules from Data Streams Decision Rules from Data Streams Feature Selection from Data Streams Visualization Techniques for Data Streams Single-Pass Algorithms Scalable Algorithms Real-Time Applications Real-World Applications GUIDELINES FOR PAPER SUBMISSION The preferred file format is PDF, in which papers' final version must be submitted. Do not compress files in any way. Submit two files: A one-page cover sheet that lists the title of the paper, the name(s) and affiliation(s) of the author(s), and the address (including e-mail address and fax number) to which correspondence should be sent. The paper itself in PDF format, with authors and affiliations omitted. Author names and addresses must not appear in the body of the paper, self-reference must be in the third person, attribution to the author(s) must be in the form of "author", and bibliographical entries by the author(s) must also be in the form of "author". Each submitted paper will be fully refereed and undergo a blind review process by at least three referees. The conference proceedings will be published by ACM. Hence, all accepted papers should be submitted in ACM 2-column camera ready format for publication in the symposium proceedings. The maximum number of pages allowed for the final papers is 5 pages. There is a set of templates to support the required paper format for a number of document preparation systems at http://www.acm.org/conferences/sac/sac2004/submission.html Accepted papers will be published in the annual conference proceedings by ACM and in the Digital Library, and also in DBLP. Please submit papers electronically by e-mail to the track co-chair aguilar@lsi.us.es (subject: DS-SAC04) Poster Publication of Selected Papers: A set of selected papers, which did not get accepted as full papers, will be accepted as poster papers and will be published as extended 2-page abstracts in the symposium proceedings. ACM SIGKDD Explorations Special Issue: We have plans to invite a selected number of accepted papers for expansion and revision for possible inclusion in an ACM SIGKDD Explorations Vol 6. Issue 1, after additional reviewing. IMPORTANT DUE DATES Sept. 6, 2003: Paper/Tutorial submissions Oct. 18, 2003: Author notification Nov. 8, 2003: Camera-Ready Copy CHAIRS Jesus S. Aguilar-Ruiz, University of Seville, Spain aguilar@lsi.us.es http://www.lsi.us.es/~aguilar/ Paul R. Cohen, University of Massachusetts, US cohen@cs.umass.edu For more information, visit http://www.lsi.us.es/~aguilar/ds/ . ------------------------------ From: Lim (mlew) Subject: MIR03 Date: Mon, 23 Jun 2003 13:12:04 +0200 CALL FOR PAPERS - MIR 2003 5th International Workshop on Multimedia Information Retrieval November 7, Berkeley, CA, USA in conjunction with ACM Multimedia 2003 Website: http://carol.wins.uva.nl/~nicu/MIR/ GENERAL INFORMATION The explosion of multimedia content in databases, broadcasts, streaming media, etc. has generated new requirements for more effective access to these global information repositories. Content extraction, indexing, and retrieval of multimedia data continues to be one of the most challenging and fastest-growing research areas. Following the success of the four previous MIR workshops held in conjunction with the ACM Multimedia Conferences, the purpose of the 5th International Workshop on Multimedia Information Retrieval (MIR 2003) is to bring together researchers, developers, and practitioners from academia and industry to discuss issues in retrieving multimedia information from libraries, databases, and streaming media sources. We are soliciting high quality original papers which address a range of issues in multimedia information retrieval including, but not limited to: * Content-based indexing, search, and retrieval of multimedia data * Multimedia data modeling and visualization * Automated semantic annotation * Metadata for multimedia retrieval * Multi-modal human-computer interaction * Query languages and query processing for multimedia retrieval * Multimedia and media mining * User perspectives and user modeling for multimedia retrieval * Semantic content analysis * Intelligent agents for multimedia indexing and retrieval * Tools, benchmarks, and standards * Multimedia retrieval for pervasive devices * New media types and new applications * Multi-modal event detection and recognition * Multi-modal/Multi-sensor fusion techniques * Indexing and retrieval from streaming media * Issues in high performance multimedia databases IMPORTANT DATES August 1, 2003: Submission of full paper August 18, 2003: Notification of acceptance August 29, 2003: Camera-ready full paper PAPER SUBMISSION Email full papers (no longer than 8 pages in the ACM style sheet in English), to lim@liacs.nl with the following information: (1) Title of paper & short abstract summarizing the main contribution (2) Names and contact info of all authors, also specifying the contact author. (3) The paper in postscript or PDF format. All submissions will be peer-reviewed by at least 3 members of the program committee. The workshop proceedings will be printed and appear in the ACM Digital Library. KEYNOTE ADDRESS Prof. David Forsyth of UC Berkeley ORGANIZING COMMITTEE Nicu Sebe, University of Amsterdam, The Netherlands Chabane Djeraba, University of Nantes, France Michael Lew, LIACS Media Lab, The Netherlands For more information, visit http://carol.wins.uva.nl/~nicu/MIR/ . ------------------------------ From: "Prof. Shlomo Argamon" Subject: CFP: JASIST special issue on Computational Approaches to Style Date: Mon, 23 Jun 2003 16:36:11 -0500 Call for Papers Special Topic Issue of _JASIST_ Computational Methods for Style Analysis and Synthesis The next Special Topics Issue of the _Journal of the American Society for Information Science and Technology_ (JASIST) is scheduled to come out in early 2004 on the topic of Computational Methods for Style Analysis and Synthesis. The guest editor for this special issue will be Shlomo Argamon of the Illinois Institute of Technology in Chicago, IL. In recent years a growing number of researchers working in a variety of different areas have focused on explicitly addressing recognition and generation of style in their various disciplines, research that contrasts with traditional emphases on 'performance' or 'content' or 'meaning'. Indeed, in some media such as music, visual art and to a lesser extent, film and even expressive speech, 'meaning' itself comprises mainly factors such as excitation and calmness or other emotional expressions that can be considered aspects of style instead of what is usually thought of as content. Achievements in computational style research include systems for authorship attribution, organizing and retrieving documents based on their writing style, composing new music in a given composer's style, rendering animation in different motion styles, and more. Work in all media shares the problem of formalizing a notion of style, and developing a modeling language that supports the representation of differing styles. Machine learning techniques are often applied to automatically determine the parameters of such models. We seek submissions that address all aspects of style analysis and synthesis from a computational perspective, but are particularly interested to see work that addresses some of the following questions: - What is style, and how may it be formalized? - What kinds of features indicate style (as opposed to function or meaning)? - How is style related to short- and long-term temporal dependencies, such as found in music or text? - How do stylistic features correlate with affect of the observer/performer? - How may style be effectively combined with pre-existing content? - What sorts of formal modeling methods are useful in representing style? - How may one effectively learn a style of expression and then execute it? - How does perceived style depend on the observer's context? - How may presentation style affect comprehension? - What connections can be drawn from stylistic methods used for one domain to another? We seek papers that discuss research in the area of Style Analysis and Synthesis in all media and from many angles. Inquiries can be made to the guest editor at argamon@iit.edu. Manuscript submissions (four copies of full articles) should be addressed to: Professor Shlomo Argamon Department of Computer Science Illinois Institute of Technology 10 W. 31st Street Chicago, IL 60616 (312) 567-5289 voice (312) 567-5067 fax argamon@iit.edu email The deadline for accepting manuscripts for consideration for publication in this special issue is August 31, 2003. All manuscripts will be reviewed by a select panel of referees, and those accepted will be published in a special issue of _JASIST_. Original artwork and a signed copy of the copyright release form will be required for all accepted papers. A copy of the call for papers will be available on the World Wide Web as is further information about _JASIST_, at http://www.asis.org/. ------------------------------ From: "Soe-Tsyr Yuan" Subject: 1st Call For Paper: IEEE International Conference one-Technology, e-Commerce and e-Service Date: Thu, 26 Jun 2003 00:33:18 +0800 1st Call For Paper: IEEE International Conference one-Technology, e-Commerce and e-Service IEEE International Conference on e-Technology, e-Commerce and e-Service (EEE-04) Grand Hotel, Taipei, Taiwan March 29-31, 2004 http://bikmrdc.lm.fju.edu.tw/eee04/ The 2004 IEEE International Conference on e-Technology, e-Commerce and e-Service(EEE-04) aims to bring together researchers and developers from diverse areas of computing, developers and practitioners to explore and address the challenging research issues on e-technology in order to develop a common research agenda and vision for e-commerce and e-business. The main focus of the conference is on the enabling technologies to facilitate next generation, intelligent e-Business, e-Commerce and e-Government. All submissions will be handled electronically and must be in PDF or PostScript format. Please see the conference web page for instructions. Accepted papers are to be included in the conference proceedings published by IEEE Computer Society. Outstanding papers at EEE-04 will be expanded and revised for inclusion in Information Systems Frontiers (a SCI-indexed international journal published by Kluwer Academic Publishers). For more details of this conference, please see or the conference web page. - Paper submissions due: November 1, 2003 - Notification of acceptance: December 20, 2003 - Camera-ready final papers due: January 20, 2004 EEE-04 Program Co-Chairs Soe-Tsyr Yuan, Fu-Jen University, Taiwan Jiming Liu, HK Baptist University, HongKong ------------------------------ From: Zia Syed Subject: FIRST CALL FOR PAPERS: ECIR-04- 26th European Conference on Information Retrieval Date: 27 Jun 2003 16:22:28 +0100 FIRST CALL FOR PAPERS 26th European Conference on Information Retrieval (ECIR-04) April 5-7, 2004 Sunderland, UK http://ecir04.sunderland.ac.uk The British Computer Society's Information Retrieval Specialist Group's annual European Conference on Information Retrieval (ECIR'04) is the main European forum for the presentation of new research results in the field of Information Retrieval. The Conference encourages the submission of high quality research papers reporting original, previously unpublished results. Topics of interest include but are not limited to the following areas: Text representation and indexing Cross-lingual and multilingual IR Metasearching and data fusion Data mining and information extraction Topic detection and tracking Text summarisation Question answering Web-based IR Information Retrieval for digital libraries Mobile IR Formal methods and language models for IR Natural Language Processing for IR Structured document retrieval, including XML Image and video retrieval Text classification (categorization or clustering) Content-based adaptive filtering and routing Usability, interactivity and visualization Search strategies User modelling and user studies Evaluation issues and test collections Distributed IR Compression and scalability in IR Architectures for IR Audio and speech retrieval Optical character recognition and IR Machine learning for IR SUBMISSION CATEGORIES FULL PAPERS The conference encourages the submission of high quality research papers that have not been previously published and are not under review for another conference or journal. Submissions will be reviewed by a panel of experts on the basis of the originality of the work, the validity of the results, chosen methodology, writing quality, and the overall contribution to the field of Information Retrieval. All accepted full papers will be published in the conference proceedings by Springer-Verlag in the Lecture Notes in Computer Science series (http://www.springer.de/comp/lncs/index.html). Submissions must be in English, which is the official language of the conference, and must not exceed 15 pages including references and figures. Papers should be submitted as PDF files through the conference web site. Submission templates and guidelines are available for download at the following address: http://www.springer.de/comp/lncs/authors.html POSTERS Poster submissions addressing any of the areas identified in the conference topics are invited. Authors are encouraged to demonstrate work in progress and late-breaking research results. The submission must include a two-page summary of the work, prepared in accordance with the template available on the conference website. All accepted posters will be published in volume two of the proceedings, which will be distributed at the conference. An A4 diagrammatic plan of the poster display is also required. Please note that because of the late deadline for submissions for this track, all posters must be submitted in camera-ready copy format. There will be no opportunity for authors to modify poster papers following the review process. For further information about poster submission please contact Dr. Michael Oakes, ECIR 2004 Posters Chair, email: ecir04posters@sunderland.ac.uk IMPORTANT DATES Deadline for Full Papers 1 November 2003 Notification for Full Papers 19 December 2003 Camera ready copy Full Papers 14 January 2004 Deadline for Posters 07 January 2004 Notification for Posters 07 February 2004 CONFERENCE VENUE The conference will be held at the School of Computing and Technology at the University of Sunderland, UK. Located on the North East Coast of England, Sunderland is one of the UK's newest cities. Standing on one of the oldest educational cites in the country, the university campus successfully blends the old with the new. To the North of the campus lies St Peter's church where the Venerable Bede was trained, marking a tradition of learning that stretches back over a thousand years. TRAVEL Sunderland is located on the North East coast of England, close to the A19 and A1. The nearest airport is Newcastle International Airport providing connections to most major UK and European cities, including London Heathrow, Gatwick, Stansted, Amsterdam Schiphol and Brussels. Direct Metro link to Newcastle Airport. Direct Metro and rail links to Newcastle Central Station, with trains to all major UK cities FURTHER INFORMATION For more details about the conference please contact the conference General Chairs: Dr. Sharon McDonald and Professor John Tait School of Computing and Technology University of Sunderland Sunderland SR6 0DD United Kingdom Email: ecir04@sunderland.ac.uk http://ecir04.sunderland.ac.uk ------------------------------ From: "ias8 Conference" Subject: IAS-8: Call for Papers Date: Tue, 1 Jul 2003 13:58:53 +0200 (CEST) CALL FOR PAPERS IAS-8: 8th Conference on Intelligent Autonomous Systems March 10-13, 2004 Amsterdam, NL www.ias8.org IAS-8 brings the Intelligent Autonomous Systems Conference back to Amsterdam, the city which also hosted the first two IAS conferences. The focus of these conferences is on intelligent systems that can directly sense and act in their own environment without demanding detailed supervision from humans. These systems are beginning to enter our daily life in ambient intelligence applications. Many new challenges are emerging to create systems that can operate and interact in human inhabited environments. SUBMISSION INFORMATION Prospective authors are invited to submit full papers in PDF or Postscript formats through the conference website www.ias8.org. Accepted papers must be presented at the conference by one of the authors in order to appear in the conference proceedings and CD. The proceedings will be published by IOS press and will be available as book and CD-ROM. IMPORTANT DATES Submission of full papers: Sept 8, 2003 Acceptance notification: Nov 17, 2003 Final paper due: Dec 15, 2003 Early registration: Dec 15, 2003 EURON MEETING The annual meeting of the European Robotics Research Network is co-located with, and immediately follows the IAS-8 conference. TOPICS include but are not limited to: Autonomous robots, Robot vision, Domestic robots, Multi-agent systems, Sociable systems, Distributed decision making, Cooperative multi-robots, Human and robot skills Humanoids, Service robotics, Health care and medical robots, Biologically inspired systems, Sensing and data fusion, Planning and control architectures, Learning and adaptive systems, Robot societies, Robots in space and underwater, Human-robot interaction, Cognitive robotics GENERAL CHAIR: Frans Groen, University of Amsterdam, The Netherlands For further information, visit http://www.ias8.org ------------------------------ From: Kevin Korb Subject: CFP: Machine Learning as Experimental Philosophy of Science Date: Fri, 4 Jul 2003 15:23:33 +1000 CALL FOR PAPERS MINDS AND MACHINES http://www.wkap.nl/journalhome.htm/0924-6495 SPECIAL ISSUE: MACHINE LEARNING AS EXPERIMENTAL PHILOSOPHY OF SCIENCE GUEST EDITORS: KEVIN KORB AND HILAN BENSUSAN Deadline: 1 December 2003 Machine learning studies inductive strategies in algorithms. The philosophy of science investigates inductive strategies as they appear in scientific practice. Although the two disciplines have developed largely independently, they share many of the same underlying problems. This is slowly coming to be recognized in a number of ways, as evidenced in the annual Uncertainty in AI and AI and Statistics conferences. This special issue will explore the extent to which the methods and resources of philosophy of science and machine learning can inform one another. In "Computational Philosophy of Science" (1988) Paul Thagard presented a challenge to the philosophical community: philosophical theories of scientific method, if they are worth their salt, should be implementable as computer programs. Contributions will address this challenge and/or the inverse challenge: both machine learning algorithms and methods for evaluating machine learning algorithms should be implementations of sensible approaches to philosophy of science. Machine learning researchers have only recently discovered the relevance of statistics and philosophical views on the foundations of statistics to evaluating the performance of their systems; we hope to carry that discussion further. The special issue will therefore focus on such questions as: 1. Can machine learning experiments tell us about inductive discovery in science? 2. What theoretical results in computational learning can be useful in understanding scientific method? How can accounts of scientific confirmation, explanation, discovery and consilience be used to develop automatic learning systems? 3. How can we assess induction? What statistical or other criteria need to be met to prefer one machine learning algorithm and/or scientific method over another? What is the role in machine learning and science of model building versus prediction? 4. Is there a substantial difference between scientific reasoning as conceived in the philosophy of science and in machine learning? 5. Is scientific method indeed mechanizable? Are scientific practices algorithmic? Instructions for Authors are available at http://www.kluweronline.com/issn/0924-6495 Inquiries and papers should be sent to: korb@csse.monash.edu.au or Dr Kevin Korb School of Computer Science and Software Engineering Monash University Clayton, Victoria 3800 Australia ------------------------------ From: Jesus Correas Fernandez Subject: ITCLS 2003 CfP - Deadline extended to July 14th, 2003 Date: Fri, 04 Jul 2003 18:26:49 +0200 [ITCLS 2003 CfP - Deadline extended to July 14th, 2003] Call for Papers and Participation COLOGNET Workshop on Implementation Technology for Computational Logic Systems (ITCLS 2003) Satellite Workshop of FME 2003 Symposium 9 September 2003, Pisa, Italy http://www.clip.dia.fi.upm.es/Conferences/ITCLS-2003/ ------------------------------ From: Geoffrey Hinton Subject: postdoctoral positions in Toronto Date: Fri, 27 Jun 2003 14:39:55 -0400 The Machine Learning Group in the Department of Computer Science at the University of Toronto is seeking two outstanding postdoctoral researchers to join our lab for up to three years starting between August 2003 and April 2004. Candidates should have a strong computational background and a keen interest in machine learning research. One postdoc will work primarily with Geoffrey Hinton on unsupervised learning of multilayer distributed representations. In addition to experience in machine learning, an interest in vision and/or computational neuroscience would be an asset for this position. The other postdoc will work primarily with Sam Roweis on machine learning, data mining, and statistical signal processing. Our group studies applied statistics and data mining as well as many aspects of computational and biological learning. Active research projects include investigations of unsupervised learning algorithms, population coding, generative models and Monte Carlo or variational methods for fitting them, kernel machines, reinforcement learning, spectral methods, Bayesian estimation, and applications to bioinformatics, collaborative filtering, text and web documents, speech and audio processing, and scientific data analysis. Currently we have the following six full time faculty members and three postdocs as well as 15 graduate students and several affiliated members in other departments and units: Faculty: Postdocs: Craig Boutilier Matt Beal Brendan Frey (ECE) Miguel Carreira-Perpinan Geoffrey Hinton Max Welling Radford Neal Sam Roweis Rich Zemel For more information, please consult our lab's website at http://learning.cs.toronto.edu The learning group in Toronto provides an exceptional critical mass of researchers interested in all aspects of statistical learning, adaptive behaviour and signal processing. Our department also has extremely strong groups in Computer Vision, Computational Linguistics, Planning and Reasoning, Theory, Database Systems and other related areas. The Department of Electrical and Computer Engineering at Toronto also has several groups engaged in research on mobile robotics, audio and video processing, distributed sensor networks, coding and communications and data compression. Toronto itself is an extremely livable, cosmopolitan metropolis with exceptional culture, food and outdoor recreation in and around the city. Applicants should send a CV, a one page statement of research interests, and a list of three references electronically to either roweis@cs.toronto.edu or hinton@cs.toronto.edu If electronic submission is not possible, fax your application to 416-978-1455, directed to the attention of either Sam Roweis or Geoffrey Hinton. ------------------------------ From: Zia Syed Subject: Phd Studentships - School of Computing, RGU, Scotland Date: 02 Jul 2003 21:04:10 +0100 School of Computing PhD Research Studentships Robert Gordon University, Scotland, UK A research studentship opportunity in the below mentioned area and others in Computing are available: Adaptive User Interfaces for Personal Information Use (please quote ref: FDT1) For application form and details on this and other studentships in School please see: http://www.rgu.ac.uk/research/degrees/page.cfm?pge=8541 http://www.scms.rgu.ac.uk/vacancies/studentships.shtml These studentships are open to all applicants, and candidates should a first or upper second class honours degree (or equivalent) in computer science or a degree with significant computing content. All successful candidates will have a tax free living allowance of £9500 (which is £500 above the normal stipend) per annum. Depending on eligibility,non-UK/EU students will need to contribute £500 per annum towards their Overseas tuition fees. Aberdeen is a superb place to live with good accommodation, excellent amenities and a large student population. The countryside surrounding Aberdeen provides myriad opportunities for hill walking,orienteering, canoeing, mountain biking, cycling,skiing and other outdoor pursuits. ------------------------------ From: "Ingemar J. Cox" Subject: Research Fellow positions at University College London (Adastral Park) Date: Fri, 04 Jul 2003 15:02:13 -0400 The Departments of Electronic Engineering and Computer Science of University College London are establishing a new postgraduate research institute at Adastral Park, near Ipswich. We currently have vacancies for three Research Fellows. These positions are intended to be equivalent to Lecturer/Senior Lecturer (assistant/associate professor) positions, but are initially for a 5 year period. Interested candidates can find further information at http://www.ucl.ac.uk/hr/vacancies/adverts/EE0040.html The application deadline is July 30. ------------------------------ From: Avi Pfeffer Subject: initial IBAL release Date: Mon, 23 Jun 2003 13:23:32 -0400 I am pleased to announce the initial release of IBAL, a general purpose language for probabilistic reasoning. IBAL is highly expressive, and its inference algorithm generalizes many common frameworks as well as allowing many new ones. It also provides parameter estimation and decision making. All this is packaged in a programming language that provides libraries, automatic type checking, etc. IBAL may be downloaded from http://www.eecs.harvard.edu/~avi/IBAL. ------------------------------ End of ML-LIST Digest Vol 15, No. 11 ************************************