From bhanupvsr at gmail.com Tue Sep 5 08:30:10 2006 From: bhanupvsr at gmail.com (Bhanu Prasad) Date: Tue, 5 Sep 2006 08:30:10 -0400 Subject: [ACT-R-users] Call for book chapters on neural networks Message-ID: <621812f80609050530h38314d32od5bceeaa0cbed23e@mail.gmail.com> *SECOND CALL FOR BOOK CHAPTER CONTRIBUTIONS* * * *SUBMISSION DEADLINE EXTENDED UNTIL OCTOBER 4 2006 * (people who already submitted their abstracts need not respond to this email) * * *Book Title: Speech, Audio, Image and Biomedical Signal Processing using Neural Networks* * * *Editors: Dr. Bhanu Prasad1 and Dr. S. R. Mahadeva Prasanna2* * * *Publisher: Springer-Verlag, Germany* * * *Year of Publication: 2007* *BACKGROUND AND MOTIVATION* * * Neural networks are being used for processing speech, audio, image and biomedical signals for many years. Some of the applications in speech processing where neural networks are extensively used include speech recognition, speaker recognition, speech enhancement, speech coding and speech synthesis. In audio processing, neural networks are used for speech/music classification, audio classification and audio indexing and retrieval. Edge extraction, texture classification, face recognition, character recognition, finger print identification, image enhancement and image coding are some of the applications of neural networks in image processing. Neural networks are also used for the identification of biomedical signals, different diseases, medical image processing and ECG signal processing. The articles related to the applications of neural networks in speech, audio, image and biomedical signal processing are spread in the literature across different journals, conference proceedings and books. The objective of this book is to provide a common platform for all the researchers working in the above mentioned areas to consolidate their research findings in the form of book chapters. Review articles on the usefulness of neural networks in the above mentioned signal processing areas are also planned to be included in this book. The proposed book is aimed to serve the research community mainly in the following ways: - The reader is equipped with the basics of signal processing like a course on digital signal processing and is interested in pursuing a research career in the application areas of signal processing. Articles on the fundamentals of speech, audio, image and biomedical signal processing and also neural networks will provide the necessary background for the beginner to start research work in these areas. - The reader has completed first courses in one of the above mentioned signal processing areas say speech processing and neural networks and is curious to know how to use neural network models in some of the tasks like speech recognition, speaker recognition and so on. For such a reader this book will be a good starting point since information about the applications of neural networks for these tasks and also rich literature related to them will be present. - The reader has used neural network models in one of the signal processing areas say speech processing and would like to know how they are and can be used in other signal processing areas like audio, image and biomedical signals. For such a reader this book will be a good source where applications of neural networks for processing different types of signals can be found. *CALL FOR ABSTRACTS* * * The prospective authors who are working in one or more of the above mentioned areas can email an extended abstract of 1500-2000 words describing the scope of the work that will be included in their proposed chapters. Since it is proposed to conduct a blind review of the submitted abstracts, it is strongly suggested not to reveal their identity in any form. The abstract needs to be submitted in WORD/PDF format and should contain only chapter title and text of abstract without any affiliation details. The author details including the affiliations should be included within the body of the email. Notification of acceptance/rejection will be intimated by email. * * *MAIL YOUR ABSTRACTS TO* * * prasanna at iitg.ernet.in and CC to srmp1944 at yahoo.co.in * * * * *NEW IMPORTANT DATES* * * Last Date for Receiving Abstract: 1st October 2006 Notification of Acceptance/Rejection: 1st November 2006 Camera Ready Version of Chapter: 1st January 2007 * * *CONTACT INFORMATION* * * Dr. S. R. Mahadeva Prasanna Department of Electronics and Communication Engineering Indian Institute of Technology Guwahati Guwahati-781039, Assam, India Email: prasanna at iitg.ernet.in and CC to srmp1944 at yahoo.co.in Tel:+91-361-2582513 (office) Fax:+91-361-2582542 Web: http://www.iitg.ernet.in/engfac/ece/public_html/srmp.htm * _________________________________________________________________________________________________ *** *1*Department of Computer and Information Sciences, Florida A&M University, Tallahassee, FL 32307 USA., email: bhanupvsr at gmail.com, bhanu.prasad at famu.edu 2Department of Electronics and Communication Engineering, Indian Institute of Technology Guwahati, Guwahati-781039, Assam, India., email: prasanna at iitg.ernet.in and CC to srmp1944 at yahoo.co.in -------------- next part -------------- An HTML attachment was scrubbed... URL: From jeedward at gmail.com Thu Sep 14 08:22:48 2006 From: jeedward at gmail.com (John Edward) Date: Thu, 14 Sep 2006 08:22:48 -0400 Subject: [ACT-R-users] Multi-conference in computer science and engineering In-Reply-To: <45086A03.90800@techexpo.com> Message-ID: <000301c6d7f8$934ee400$6401a8c0@cisnotebookbp> *Apologies for cross posting. Please forward to interested people* The 2007 International Multi-Conference in Computer Science, Engineering, and Information Science will be held during 9-12 of July 2007 in Orlando, FL, USA. The multi-conference consists of four major events namely International Conference on Artificial Intelligence and Pattern Recognition (AIPR-07) International Conference on Enterprise Information Systems and Web Technologies (EISWT-07) International Conference on High Performance Computing, Networking and Communication Systems (HPCNCS-07) International Conference on Software Engineering Theory and Practice (SETP-07) All these events will be held simultaneously at the same place. Click on www.PromoteResearch.org for more information. Sincerely John Edward Publicity committee co-chair Email: jeedward [at] gmail.com PS: please send an email to the above address in case you are not interested on further emails on this event. -------------- next part -------------- An HTML attachment was scrubbed... URL: From Glenn.Gunzelmann at mesa.afmc.af.mil Thu Sep 14 18:03:49 2006 From: Glenn.Gunzelmann at mesa.afmc.af.mil (Gunzelmann Glenn F Civ AFRL/HEAT) Date: Thu, 14 Sep 2006 18:03:49 -0400 Subject: [ACT-R-users] Position Available Message-ID: The Performance and Learning Models Team at the Air Force Research Laboratory's Mesa Research Site near Phoenix, AZ is looking for a talented cognitive scientist to lead the development of mechanisms to account for the impacts of fatigue on human cognition and performance. This position requires U.S. citizenship. The ideal candidate will have interest and experience in developing computational models of human cognition using a cognitive architecture (we are using ACT-R in this research). While we envision filling this position with an individual who has recently completed a Ph.D., we are somewhat flexible on this, including possible opportunities for long graduate research internships (i.e., 6-12 months) or visiting faculty appointments (e.g., sabbatical visits). We hope to fill this position during this fall or winter, which is a perfect time to move to the Valley of the Sun. If you are interested, or if you would like additional information, please contact me. Thanks, -Glenn Email: glenn.gunzelmann at mesa.afmc.af.mil Phone: 480-988-6561, x674 _________________________________ Glenn Gunzelmann, Ph.D. Research Psychologist Air Force Research Laboratory _________________________________ -------------- next part -------------- An HTML attachment was scrubbed... URL: From k.g.langendoen at tudelft.nl Mon Sep 18 05:43:20 2006 From: k.g.langendoen at tudelft.nl (k.g.langendoen at tudelft.nl) Date: Mon, 18 Sep 2006 11:43:20 +0200 Subject: [ACT-R-users] CFP: Fourth International Conference on Networked Sensing Systems (INSS 2007) Message-ID: [Apologies if you receive multiple copies of this e-mail] ******************************************************************************** Call For Papers Fourth International Conference on Networked Sensing Systems (INSS 2007) June 6-8, 2007 Braunschweig, Germany http://www.inss-conf.org Sponsored by Transducer Research Foundation ******************************************************************************** During the past years the INSS is established as THE scientific event where academic and industrial experts from the areas of sensor, networks and applications on sensor networks come together. The INSS provides a forum to hear about the hottest developments in these areas, to exchange ideas and to start up collaborations within these fields and between industry and academia. INSS 2007 is the fourth annual conference with a selective single-track technical programs. The International Conference on Networked Sensing Systems invites outstanding research papers from the field of sensor technology, wireless networking or application of networked sensor systems. The conference especially encourages submissions that are suitable and should be of interest for the researchers from all three fields. Topics include but are not limited to: - Applications of Networked Sensing Systems - Prototypes, field studies, and testbeds for Networked Sensing Systems - Security for Networked Sensing Systems - Data management for Networked Sensing Systems - Middleware for Networked Sensing Systems - Communication protocols - Sensor Phenomena and Modeling - Sensing Systems - Sensors - Sensors Materials and Fabrication INSS 2007 invites the submission of both regular and BOF papers. Regular papers must be no more than 8 two-column pages (minimum 4 pages) long and include an abstract of 100 - 150 words. Birds-of-Feather (BoF) papers must be no more than 4 two-column pages long and include an abstract of 100 -150 words. BoF papers are suitable for interactive discussions; the presenters of accepted BoF papers are given short oral presentation and interactive poster discussion. INSS2007 is seeking papers interesting to the interdisciplinary community represented at the conference. Papers will be evaluated on the basis of originality, significance of the contribution to the field, technical correctness and presentation. Papers will be peer-reviewed. Papers submitted must not be under simultaneous review for any other conference, journal, workshop or other publication. Papers should be formatted according to IEEE transaction format. Accepted papers will be included in the conference proceedings. Authors are required to attend the conference to present their work. Important Dates Paper Submission Deadline: December 1, 2006 Notification of Acceptance: February 5, 2007 Camera-Ready Papers: March 15, 2007 Organization General Co-chairs: Michael Beigl, University of Braunschweig, Germany Shuichi Shoji, Waseda University, Japan Program Chair: Hideyuki Nakashima, Future University-Hakodate, Japan Program Vice-chairs: Harri Kopola, VTT, Finland Tian He, University of Minnesota, USA Yoshito Tobe, Tokyo Denki University, Japan Publicity Co-chairs: Suzumu Ishihara, Shizuoka University, Japan Koen Langendoen, Delft University of Technology, Netherlands Darrin Young, Case Western Reserve University, USA From fomi at loa-cnr.it Wed Sep 20 11:40:10 2006 From: fomi at loa-cnr.it (fomi) Date: Wed, 20 Sep 2006 17:40:10 +0200 Subject: [ACT-R-users] [Applied Ontology] CFC: Special issue on Formal Ontologies for Communicating Agents Message-ID: ****************************** CALL FOR CONTRIBUTIONS ************************************************************************ ****************** Following FOCA, workshop held at ESSLLI from July 31 to August 4, 2006 (http://www.loa-cnr.it/esslli06/): Formal Ontologies for Communicating Agents, special issue for the journal Applied Ontology (http://www.applied-ontology.org/) ************************************************************************ ****************** GUEST EDITORS OF THE SPECIAL ISSUE: Roberta Ferrario (ferrario at loa-cnr.it) Laurent Prevot (prevotlaurent at gate.sinica.edu.tw) ************************************************************************ ****************** PURPOSE OF THE SPECIAL ISSUE : Following the workshop "Formal Ontologies for Communicating Agents" that took place within the last ESSLLI summer school in Malaga, we would like to invite contributions for a special issue of the international journal ''Applied Ontology''. We especially invite the authors of the paper presented at FOCA 2006 to submit an extended version of their contribution. However, anyone is invited to submit a relevant contribution for the topic of the special issue described below. ************************************************************************ ***************** DESCRIPTION: In recent years lots of efforts have been devoted to formal studies of human and artificial agent communication. Research advancements have been achieved along three main lines: (i) agent's internal states and dynamics, (ii) social interaction and conventional communicative patterns, (iii) semantics-pragmatics interface - especially in the dialogue context (i.e. the interplay between the semantic content of messages and the communicative acts themselves). There is a recent trend of studies trying to integrate these approaches in many ways. On the other hand, formal ontology has been consecrated as a good solution for comparing and integrating information and thus its application to this specific domain is very promising . More precisely, an ontological analysis of the fundamental ingredients of interaction and communication will make explicit the hidden ontological assumptions underlying all these proposals. Ontology has also proven to be a very powerful means to address issues related to the exchange of meaningful communication across autonomous entities, which can organize and use information heterogeneously. The purpose of this special issue is therefore to gather contributions that (i) take seriously into account the ontological aspects of communication and interaction and (ii) use formal ontologies for achieving a better semantic coordination between interacting and communicating agents. ************************************************************************ **************** MAIN TOPICS: We encourage contributions concerning the two main areas listed below with a particular attention to explore the interplay between ontological analysis and its applications in practical cases. * Ontological aspects of interaction and communication - Ontological analysis of interaction and communication - Studies on the structure and coherence of interaction - Logical models for communicative acts - Primitives of interaction and communication - Formal semantics of dialogue (dealing with ontological issues) *Semantic coordination through formal ontologies - Dialogue semantics and formal ontology - Dynamic ontology sharing - Ontological primitives for meaning negotiation, ontological alignment and semantic interoperability - Ontology evolution through communication - Concrete problems and experiences in terminological disambiguation and integration ************************************************************************ ***************** ABOUT THE JOURNAL: Although a formal contribution is not an absolute requirement for contributing to Applied Ontology, the contributors should keep in mind the aim and scope of Applied Ontology, an interdisciplinary journal of Ontological Analysis and Conceptual Modeling. Applied Ontology is a new journal whose focus is on information content in its broadest sense. As the subtitle makes clear, two broad kinds of content-based research activities are envisioned: ontological analysis and conceptual modeling. The former includes any attempt to investigate the nature and structure of a domain of interest using rigorous philosophical or logical tools; the latter concerns the cognitive and linguistic structures we use to model the world, as well as the various analysis tools and methodologies we adopt for producing useful computational models, such as information systems schemes or knowledge structures. Applied Ontology is the first journal with explicit and exclusive focus on ontological analysis and conceptual modeling under an interdisciplinary view. It aims to establish a unique niche in the realm of scientific journals by carefully avoiding unnecessary duplication with discipline-oriented journals. For this reason, authors will be encouraged to use language that will be intelligible also to those outside their specific sector of expertise, and the review process will be tailored to this end. For example, authors of theoretical contributions will be encouraged to show the relevance of their theory for applications, while authors of more technological papers will be encouraged to show the relevance of a well-founded theoretical perspective. Moreover, the journal will publish papers focusing on representation languages or algorithms only where these address relevant content issues, whether at the level of practical application or of theoretical understanding. Similarly, it will publish descriptions of tools or implemented systems only where a contribution to the practice of ontological analysis and conceptual modeling is clearly established. ************************************************************************ ****************** SUBMISSION DETAILS: Submissions, that will undergo a peer-reviewing process, must be sent electronically through the journal's website (http://www.applied-ontology.org/) by the deadline listed below. Detailed instructions for authors are available from the same website. ************************************************************************ ****************** IMPORTANT DATES: Submissions December 20, 2006 Notification February 21, 2007 Camera-ready April 25, 2007 Special Issue Winter 2007 ************************************************************************ ****************** From rickl at umich.edu Fri Sep 22 09:22:36 2006 From: rickl at umich.edu (Richard L. Lewis) Date: Fri, 22 Sep 2006 09:22:36 -0400 Subject: [ACT-R-users] new article on working memory & sentence comprehension Message-ID: Hi everyone: Attached is a new article that appears in the upcoming issue of Trends in Cognitive Science: Lewis, R. L., Vasishth, S. and Van Dyke, J. A. (2006) Computational principles of working memory in sentence comprehension. Trends in Cognitive Science, 10: 447-454. This article provides an overview of the theory of sentence processing (mostly syntactic parsing at this point) we have been developing that is grounded in ACT-R, and the relevant cross- linguistic empirical phenomena. It is a kind of companion article to the more detailed account of the model in the 2005 Cognitive Science journal article, but both less detailed and broader in scope. The PDF also includes the front cover of the issue, which has a picture of me contemplating my inbox. cheers, Rick ? -------------------------- Richard L. Lewis rickl at umich.edu Associate Professor http://www-personal.umich.edu/~rickl/ Department of Psychology Voice: (734) 763-1466 University of Michigan Fax: (734) 763-7480 530 Church Street Office: East Hall 4428F Ann Arbor, MI 48109-1043 -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: lewis-vasishth-vandyke-2006-tics.pdf Type: application/pdf Size: 608030 bytes Desc: not available URL: -------------- next part -------------- An HTML attachment was scrubbed... URL: From jleitao at ci.uc.pt Fri Sep 22 07:19:32 2006 From: jleitao at ci.uc.pt (=?ISO-8859-1?Q?Jos=E9_Leit=E3o?=) Date: Fri, 22 Sep 2006 12:19:32 +0100 Subject: [ACT-R-users] Last Cfp : DAARC'2007 - The 6th Discourse Anaphora and Anaphor Resolution Colloquium Message-ID: <5c7c1de2717c6b51dd659151065618a3@ci.uc.pt> LAST CALL FOR PAPERS The 6th Discourse Anaphora and Anaphor Resolution Colloquium (DAARC'2007) Lagos (Algarve), Portugal hosted by University of Lisbon, Faculty of Sciences March 29-30, 2007 http://daarc2007.di.fc.ul.pt/ Anaphora is a central topic in the study of natural language and has long been the object of research in a wide range of disciplines such as theoretical, corpus and computational linguistics, philosophy of language, cognitive science, psycholinguistics and cognitive psychology. On the other hand, the correct interpretation of anaphora has played an increasingly vital role in real-world natural language processing applications, including machine translation, automatic abstracting, information extraction and question answering. As a result, the processing of anaphora has become one of the most productive topics of multi- and inter-disciplinary research, and has enjoyed increased interest and attention in recent years. In this context, the Discourse Anaphora and Anaphor Resolution Colloquia (DAARC) have emerged as the major regular forum for presentation and discussion of the best research results in this area. Initiated in 1996 at Lancaster University and taken over in 2002 by the University of Lisbon, the DAARC series established itself as a specialised and competitive forum for the presentation of the latest results on anaphora processing, ranging from theoretical linguistic approaches through psycholinguistic and cognitive work to corpus studies and computational modelling. The sixth Discourse Anaphora and Anaphor Resolution Colloquium (DAARC?2007) will take place in Lagos (Algarve), Portugal, in March 29-30, 2007. We would like to invite anyone currently researching in the areas of discourse anaphora and anaphor resolution, from any methodological perspective or framework, to submit a paper to DAARC'2007. *The closing date for submission is October 16, 2006.* Notification of acceptance will be sent by December 15, 2006. Final versions of selected papers to be included in the proceedings are expected by January 19, 2007. Submissions (extended abstracts) must be anonymous and at most 3 pages in length. For further details on the submission procedure, and other relevant info on the colloquium visit its website at: http://daarc2007.di.fc.ul.pt/ Program Committee: Mijail Alexandrov-Kabadjov, Univ Essex Mira Ariel, Tel Aviv Univ Sergey Avrutin, OTS Amit Bagga, Ask.com Patricio Martinez Barco, Univ Alicante Peter Bosch, Univ Osnabrueck Ant?nio Branco, Univ Lisbon Donna Byron, Ohio State Univ Francis Cornish, Univ Toulouse-Le Mirail Dan Cristea, Univ Iasi Robert Dale, Macquarie Univ Richard Evans, Univ Wolverhampton Martin Everaert, OTS Lyn Frazier, MIT Claire Gardent, CNRS/Loria Rafael Mu?oz Guillena, Univ Alicante Jeanette Gundel, Univ Minnesota Sanda Harabagiu, Univ Texas at Dallas Lars Hellan, Norwegian Univ of Science and Technology Erhard Hinrichs, Univ Tuebingen Graeme Hirst, Univ Toronto Yan Huang, Univ Reading Andrew Kehler, Univ California San Diego Andrej Kibrik, Russian Academy of Sciences Emiel Krahmer, Tilburg Univ Shalom Lappin, King's College Tony McEnery, Lancaster Univ Ruslan Mitkov, Univ Wolverhampton Jill Nickerson, Ab Initio Software Corp Constantin Orasan, Univ. Wolverhampton Maria Mercedes Pi?ango, Yale Univ Georgiana Puscasu, Univ Wolverhampton Costanza Navarretta, CST Massimo Poesio, Univ Essex Eric Reuland, OTS Jeffrey Runner, Univ of Rochester Antonio Fernandez Rodriguez, Univ Alacant Tony Sanford, Glasgow Univ Fr?d?rique Segond, Xerox Research Centre Europe Roland Stuckardt, Univ Frankfurt am Main Joel Tetreault, Univ. Rochester Renata Vieira, Unisinos Organisers: Antonio Branco, Univ Lisbon Tony McEnery, Lancaster Univ Ruslan Mitkov, Univ Wolverhampton F?tima Silva, Univ Oporto From rsun at rpi.edu Fri Sep 22 10:11:03 2006 From: rsun at rpi.edu (Professor Ron Sun) Date: Fri, 22 Sep 2006 10:11:03 -0400 Subject: [ACT-R-users] IJCNN 2007 in Orlando, Florida Message-ID: <563F2BB7-F459-4C82-92CF-28C7F01B5E98@rpi.edu> IJCNN 2007 Call For Papers 2007 International Joint Conference on Neural Networks Orlando, Florida August 12-17, 2007 Celebrating 20 years of Neural Networks! http://www.ijcnn2007.org The 2007 International Joint Conference on Neural Networks (IJCNN 2007), sponsored by the International Neural Network Society and co- sponsored by the IEEE Computational Intelligence Society, is the premier event in the field of neural networks. It covers all topics in neural network theories and applications, including, but not limited to: - Neural network models and analysis - Connectionist cognitive science and cognitive modeling (language, reasoning, perception, learning, memory, consciousness, emotion, etc.) - Computational neuroscience - Neuroengineering - Cognitive robotics, developmental robotics, and neural robotics - Data analysis and pattern recognition - Signal processing and image processing - Neural control - Neuroinformatics - Hybrid neural-symbolic, neuro-fuzzy, neuro-evolutionary systems, etc. - Bayesian models and other graphical models - Kernel methods - Learning methods: supervised, unsupervised, and reinforcement - Approximate dynamic programming and neural network approaches to optimization - Neural dynamics, complex systems, and chaos - Hardware implementations of neural networks and neuromorphic engineering - Neural networks applications (expert systems, embedded systems, data mining, Multi-agent systems, financial engineering, bioinformatics, telecommunication, manufacturing, etc.) IJCNN 2007 will feature plenary speakers, special sessions, moderated panel discussions, pre-conference tutorials, post-conference workshops, regular technical sessions, poster sessions, and social functions. Prospective authors are invited to submit complete papers of no more than six (6) pages (including results, figures, tables, and references) in IEEE two-column format. Authors should submit their papers in PDF through the online submission system, which will be available at the website: http://www.ijcnn2007.org. Call for Special Sessions and Panel Discussions: The IJCNN 2007 Program Committee solicits proposals for special sessions and panel discussions within the technical scope of the conference. Special sessions and panel discussions are to be organized by experts and aimed to bring together researchers around a focused topic. Special sessions and panel discussions have become both a tradition and an important component of the IJCNN. Papers submitted for special sessions or panel discussions are to be peer-reviewed with the same criteria used for regular contributed papers. Researchers interested in organizing a special session or a panel are invited to submit a formal proposal to the Special Sessions Chair or the Panels Chair, respectively. Special session or panel proposals should include the session title, a brief description of its scope, motivation, its appeal to the attendees of this conference, organizer names and contact information, and brief CVs of the organizers. Call for Pre-Conference Tutorials and Post-Conference Workshops: IJCNN 2007 will feature a number of pre-conference tutorials and post-conference workshops covering fundamental and advanced topics in neural networks (broadly defined). Pre-conference tutorial and post-conference workshop proposals, submitted to the Tutorials Chair and Workshops Chair, respectively, are requested, and should include title, outline, motivation, appeal to the conference attendees, expected enrollment, and organizers' CVs. Important Dates: Special Session and Panel Discussion Proposals: November 31, 2006 Paper Submission: January 31, 2007 Pre-Conference Tutorial and Post-Conference Workshop Proposals: January 31, 2007 Decision Notification: March 31, 2007 Camera-Ready Submission: April 30, 2007 Further information: http://www.ijcnn2007.org General Chair: Jennie Si Arizona State University Program Chair: Ron Sun Rensselaer Polytechnic Institute ======================================================== Professor Ron Sun Cognitive Science Department Rensselaer Polytechnic Institute 110 Eighth Street, Carnegie 302A Troy, NY 12180, USA phone: 518-276-3409 fax: 518-276-3017 email: rsun at rpi.edu web: http://www.cogsci.rpi.edu/~rsun ======================================================= From galk at cs.biu.ac.il Sat Sep 30 18:03:23 2006 From: galk at cs.biu.ac.il (Gal Kaminka) Date: Sun, 1 Oct 2006 01:03:23 +0300 Subject: [ACT-R-users] Statement of Interest: Workshop on Evaluating Architectures for Intelligence Message-ID: <200610010103.24885.galk@cs.biu.ac.il> (Apologies if you receive this more than once.) Hello, We are proposing to AAAI a workshop on evaluating Architectures for Intelligence (see draft proposal below). To convince AAAI of the need for the workshop, we would like to get a count of the number of tentatively interested participants. If you feel that you or your student may find this workshop interesting, and may wish to attend or actively participate, please let us know at galk at cs.biu.ac.il We would also appreciate any comments you may have about the draft proposal for the workshop and its suggested format. Thank you! Gal Kaminka and Catherina Burghart ------------------- Draft proposal below ------------------- Workshop Proposal: Evaluating Architectures for Intelligence (Draft proposal) 1 Purpose and Scope =================== Cognitive architectures form an integral part of robots and agents. Architectures structure and organize the knowledge and algorithms used by the agents to select actions in dynamic environments, plan and solve problems, learn, and coordinate with others. Architectures enable intelligent behavior by agents, and serve to integrate general capabilities expected of an intelligent agent (e.g., planning and learning), to implement and test theories about natural or synthetic agent cognition, and to explore domain-independent mechanisms for intelligence. The evaluation of architectures has always been challenging. Several common methodologies have been applied: Showing the architecture allows behavior not previously demonstrated, demonstrating generality by application to several different domains or tasks, and compatibility with psychological data. In a few cases, architectures have been evaluated comparatively, in the context of a specific task. On the one hand, this is due to the different nature of the cognitive architectures applied; on the other hand, few appropriate methods exist. As AI research has improved in formal and empirical rigor, traditional evaluation methodologies for architectures have sometimes proved insufficient. On the formal side, rigorous analysis has often proven elusive; we seem to be missing the notation required for formally proving properties of architectures. On the empirical side, experiments which demonstrate generality are notoriously expensive to perform, and are not sufficiently informative. And at a high-level, evaluation is difficult because the criteria are not well defined: Is it generality? Ease of programmability? Compatibility with data from biology and psychology? Yet interest in architectures has not died, and in fact has even increased in recent years. There are several major research thrusts by funders (e.g., DARPA, Europe's FP6 program) and by researchers (e.g., in cognitive modeling and cognitive robotics). Recognizing that scientific progress depends on the ability to conduct informative evaluation (by experiment or formal analysis), we are proposing a workshop that will address the methodologies needed for evaluating architectures. The focus will be on methodology, rather than specific architectures. The workshop will have two goals: To promote discussion and to propose accepted evaluation criteria. 1.1 Key Issues for Discussion ----------------------------- The following key questions will be raised to motivate the workshop discussion, with the goal of providing answers (or at least steps towards answers) within a two-day workshop: o Which functions/characteristics turn an architecture into a cognitive architecture? o Are different types of evaluation needed for different types of cognitive architectures? o Are there any relevant formal methods? Can we prove properties of architectures? o What are the criteria and scales of evaluation? o How are architectures to be compared in an informative manner? o What are the underlying hypotheses one may explore with architectures? o How should we validate the design of a cognitive architecture? o How can data-sets and benchmarks (standardized tasks) be used to evaluate architectures? 1.2 Impact: Usable Guidelines for Evaluation -------------------------------------------- The goal of the workshop is to propose guidelines for evaluation of architectures, that would be acceptable to the AI community, and allow researchers both to evaluate their own work, and to better assess the progress of others. The format of the workshop (see below) will focus on developing guidelines for evaluating architectural features, conduct comparative studies, and prove architectural properties. The format will take into account the experiences of all attendees. The intention is to produce a citeable source of evaluation guidelines, which will have significant impact on designers and investigators of cognitive architectures. Such guidelines facilitate objective and reproducible evidence of an architecture's capability to solve intricate problems in the intended manner. To do this, we intend to publish the results in a special issue of an international journal. We will set up a web site with the presentation slides and explanatory material. This online resource will serve as a portal to evaluation methodology, much like similar pages have in the past been used to promote standards or appropriate use of empirical methods. We will also consider making an edited version of the workshop video recordings available. 2 Proposed Format ================= There are many researchers investigating architectures, but surprisingly little published work on evaluation methodology. As the aim of the proposed workshop is to produce the evaluation guidelines, and to address the key questions, we choose a setting enabling a good working atmosphere. The format combines information about different architecture types and evaluation methods, panels, and moderated group discussions. We see two alternative perspectives on evaluating architectures. On one hand, it makes sense to divide up the talks by architecture types (e.g., architectures implementing cognitive psychological theories, architectures inspired by biology, architectures exploiting concepts from control or rationality, architectures for coordinating agents, etc.). This makes sense because different types of architectures may require different evaluation methodologies. But it is also problematic because architectures may fall between the cracks, or fit more than one category. On the other hand, dividing up the talks by evaluation methods (e.g., comparison to human performance data, comparative studies, formal methods, etc.) may also be inappropriate, as not all evaluation methods apply everywhere. 2.1 Workshop Format ------------------- We are therefore considering a format in which we will mix these two perspectives. The first day's morning sessions will include talks grouped by different types of architectures. We believe that most of these will be contributed through the submission process. Although the talks will necessarily touch on specific architectures, their focus will be on evaluation, not on the features of the architectures. An invited panel will conclude these sessions. We will then switch gears to sessions that focus on evaluation methodologies, outside the context of architecture types. These sessions focus on invited and contributed talks, grouped along evaluation approaches: Formal methods, empirical comparative studies, benchmarks and datasets, other empirical methods, case studies (classification dependent on contributions). Each group of talks will be arranged as a moderated panel with a moderator posing prepared questions and opening questions to the audience. In particular, we will ask the panels to also consider the preceding sessions, on different types of architectures. Our final phase of the work is contingent on the size of the audience. The plan is to have audience participating in generalizing and summarizing the lessons learned. After an opening defining three key challenges (selected from the the preceding panels), we will follow an iterative process of (1) splitting into groups for discussions, each headed by an invited moderator; (2) presenting the results to everyone in the workshop (plenum); (3) getting feedback and questions. These three steps will be repeated. We may request re-splitting into groups, to make sure everyone has a chance to provide input on each type of architecture or evaluation methodology. The moderator of each group will be responsible for generating an outline for a research note explaining the evaluation methods and how they should be applied. A short summary of these outlines concludes the workshop. We believe the workshop will run for two days, but this depends on interest and number of contributed talks. We will record all proceedings. The number of attendees will not be limited, but registration will be required. 2.2 Post-workshop Documentation ------------------------------- All the panel results, video recordings and presentation materials will be collected for the web site. After the workshop, we will solicit articles from the different groups for the special issue, and for the workshop web page. 3 Organizers and Relevant Expertise =================================== The workshop will be co-chaired by Gal A. Kaminka and Catherina Burghart. The organization committee includes other members (listed below) who have all expressed interest in participating and contributing. Gal A. Kaminka (galk at cs.biu.ac.il) ---------------------------------- Gal Kaminka has been working with autonomous agents robots for the past ten years. Much of his research has focused on developing distributed teamwork architectures for multi-agent and multi-robot systems. He has been a chair and co-chair of the MOO annual workshops (at AAMAS, IJCAI, and AAAI) which focus on plan- and activity- recognition, program co-chair of the European workshop on Multi-Agent Systems (EUMAS 2005), and of the RoboCup 2002 Symposium. He has also served in other organizational roles, including AAMAS doctoral mentoring chair (2004) and Senior Program Committee member at AAAI and AAMAS (2005-2007). Catherina Burghart (burghart at ira.uka.de) ---------------------------------------- Catherina Burghart has been working with intelligent robots for the past eight years. She is a member of the German Humanoids Project, where she heads the working group on the cognitive architecture of their robot. Organizing Committee -------------------- The co-chairs are supported by a distinguished list of organizers, all of whom have had significant experience both in organization and in relevant research. The list includes: TBD (To Be Determined) -- ----------------------------------------------------------------------- Gal A. Kaminka, Ph.D. http://www.cs.biu.ac.il/~galk Assistant Professor Computer Science Dept. Bar Ilan University Only those who see the invisible can do the impossible "Death is an engineering problem." -- Bart Kosko, "Fuzzy Thinking" "But life is not an engineering task." -- Gal A. Kaminka