From owner-gann-list Thu Nov 2 17:50:03 1995 Received: (from mdomo@localhost) by cs.iastate.edu (8.7.1/8.7.1) id RAA28988 for gann-list-outgoing; Thu, 2 Nov 1995 17:13:54 -0600 (CST) Received: from ren.cs.iastate.edu (ren.cs.iastate.edu [129.186.3.41]) by cs.iastate.edu (8.7.1/8.7.1) with ESMTP id RAA28944 for ; Thu, 2 Nov 1995 17:13:20 -0600 (CST) From: GANN List Admin Received: (from gannadm@localhost) by ren.cs.iastate.edu (8.7.1/8.7.1) id RAA24646 for gann-list@cs.iastate.edu; Thu, 2 Nov 1995 17:13:03 -0600 (CST) Reply-To: giles@research.nj.nec.com (Lee Giles) X-Originator: giles@research.nj.nec.com (Lee Giles) Date: Wed, 1 Nov 95 15:51:41 EST Message-Id: <9511012051.AA24762@alta> To: gannadm@cs.iastate.edu Subject: Call For Papers Sender: owner-gann-list@cs.iastate.edu Precedence: bulk CALL FOR PAPERS: Third International Colloquium on Grammatical Inference (ICGI-96) Montpellier (France), September 25-27, 1996 With the help of the Special Interest Group in Natural Language Learning (SIGNLL) of the ACL. Chairperson: Laurent Miclet (IRISA-ENSSAT, Lannion, France) miclet@enssat.fr Organization : Colin de la Higuera (LIRMM, Montpellier, France) cdlh@lirmm.fr Scientific Committee J. Berstel (University Paris 6, France) M. Brent (J. Hopkins University, USA) H. Bunke (University of Bern, Switzerland) C. Cardie (Cornell University, USA) W. Daelemans (KUB, Nederlands) P. Dupont (FT-CNET, France) O. Gascuel (LIRMM, France) C. L. Giles (NEC Princeton, USA) J. Gregor (University of Tennessee, USA) J. P. Haton (CRIN-INRIA, France) F. Jelinek (J. Hopkins University, USA) T. Knuutila (University of Turku, Finland) S. Lucas (University of Essex, England) D. Luzeaux (=05ETCA, France) D. Magerman (Renaissance Technology, USA) E. Makinen (University of Tampere, Finland) R. Mooney (University of Texas, USA) G. Nagaraja (IIT Bombay, India) J. Nicolas (IRISA, France) J. Oncina, University of Alicante, Spain) L. Pitt (University of Illinois, USA) D. Powers (Flinders University, Australia) Y. Sakakibara (Fujitsu Laboratories Ltd, Japan) A. Stolcke (SRI International, Menlo Park, USA) E. Vidal (Universidad Politechnica de Valencia, Spain) Grammatical Inference (GI) is broadly understood as Machine Learning of Grammars and Languages from data. Traditionally, GI has been studied within several contexts: Information Theory, Formal Languages Theory, Computational Linguistics, Machine Learning, Pattern Recognition, Computational Learning Neural Networks, etc. This multidisciplinary perspective, however, has lead so far to a lack of a focused research community. A first attempt to correct this started with the "First Colloquium on Grammatical Inference : Theory, Applications and Alternatives" held in the University of Essex (U.K.), in April 1993. Then followed the "International Colloquium on Grammatical Inference 1994", held in Alicante (Spain), which proceedings have been published by Springer-Verlag as Volume 862 of the Lectures Notes in Artificial Intelligence. Following these successful meetings, ICGI 96 keeps aiming to provide a forum for discussion of principles, theory and applications of all those aspects of Machine Learning that explicitly focus on Grammars and Languages. Within this framework, topics of interest include, but are not limited to, the following : * Learning Paradigms for Grammars and languages : Cognitive models, Algebraic aspects, Identification in the limit and PAC-Learning ; Stochastic and Corpus-based approaches, Neural Networks, Genetic Algorithms, Fuzzy systems, etc. * Algorithms. * Heuristics. * Benchmarks. * Applications : Natural Language Processing, Language Translation ; Biological Sequences and Time Series Modelization and Prediction ; Image and Speech Recognition, Discrete Events Systems, etc. SCHEDULE : April 1, 1996 Deadline for submitted papers. June 15, 1996 Notification of acceptance and referrees comments. July 15, 1996 Camera ready copy. September 25-27, 1996 Colloquium. Please submit (not via electronic mail) three copies of your full length article (maximum 12 pages, 12 pt. font, including figures, tables, references, etc.) to : L. Miclet IRISA-ENSSAT BP 447 - 6, Rue de K=E9rampont 22305 LANNION Cedex FRANCE The Proceedings of the Colloquium will be considered for publication as a volume in the Springer-Verlag Lecture Notes Series in Artificial Intelligence. Information on ICGI'96 is on the www page : http://itkwww.kub.nl:2080/itk/Docs/Projects/Walter/icgi.html Laurent Miclet ENSSAT ________________________________________________________________ Ecole Nationale Sup=E9rieure de Sciences Appliqu=E9es et Technologie BP 447 6, rue de K=E9rampont Tel : +33 96 46 66 28 22305 LANNION Cedex Fax : +33 96 37 01 99 =46RANCE ________________________________________________________________ -- C. Lee Giles / Computer Sciences / NEC Research Institute / 4 Independence Way / Princeton, NJ 08540, USA / 609-951-2642 / Fax 2482 http://www.neci.nj.nec.com/homepages/giles.html == From owner-gann-list Thu Nov 2 17:50:06 1995 Received: (from mdomo@localhost) by cs.iastate.edu (8.7.1/8.7.1) id RAA28894 for gann-list-outgoing; Thu, 2 Nov 1995 17:11:41 -0600 (CST) Received: from ren.cs.iastate.edu (ren.cs.iastate.edu [129.186.3.41]) by cs.iastate.edu (8.7.1/8.7.1) with ESMTP id RAA28875 for ; Thu, 2 Nov 1995 17:11:31 -0600 (CST) From: GANN List Admin Received: (from gannadm@localhost) by ren.cs.iastate.edu (8.7.1/8.7.1) id RAA23588 for gann-list@cs.iastate.edu; Thu, 2 Nov 1995 17:11:19 -0600 (CST) Reply-To: peter@ai.iit.nrc.ca (Peter Turney) X-Originator: peter@ai.iit.nrc.ca (Peter Turney) Date: Mon, 30 Oct 1995 08:16:12 +0500 Message-Id: <9510301316.AA08917@ksl0j.iit.nrc.ca> To: gann@cs.iastate.edu Subject: Baldwin Effect Bibliography Cc: peter@ai.iit.nrc.ca X-Sun-Charset: US-ASCII Sender: owner-gann-list@cs.iastate.edu Precedence: bulk ----------------------------------------------------------------------------- Baldwin Effect Bibliography We are pleased to announce a bibliography of papers on the Baldwin effect. The Baldwin effect lies at the intersection of Machine Learning and Genetic Algorithms. The bibliography is in hypertext, with links to many of the authors and papers. The URL is: http://ai.iit.nrc.ca/baldwin/bibliography.html Any coments, corrections, or additions are welcome. Sincerely, Peter Turney, peter@ai.iit.nrc.ca Darrell Whitley, whitley@CS.ColoState.EDU Russell Anderson, rwa@milo.berkeley.edu ----------------------------------------------------------------------------- From owner-gann-list Thu Nov 2 17:50:05 1995 Received: (from mdomo@localhost) by cs.iastate.edu (8.7.1/8.7.1) id RAA28897 for gann-list-outgoing; Thu, 2 Nov 1995 17:11:41 -0600 (CST) Received: from ren.cs.iastate.edu (ren.cs.iastate.edu [129.186.3.41]) by cs.iastate.edu (8.7.1/8.7.1) with ESMTP id RAA28846 for ; Thu, 2 Nov 1995 17:11:10 -0600 (CST) From: GANN List Admin Received: (from gannadm@localhost) by ren.cs.iastate.edu (8.7.1/8.7.1) id RAA23425 for gann-list@cs.iastate.edu; Thu, 2 Nov 1995 17:10:47 -0600 (CST) Reply-To: ipmu96@robinson.ugr.es (Congreso IPMU96) X-Originator: ipmu96@robinson.ugr.es (Congreso IPMU96) Date: Fri, 27 Oct 95 09:09:06 GMT Message-Id: <9510270909.AA28689@robinson.ugr.es> To: gannadm@cs.iastate.edu Subject: IPMU'96 NEW INFORMATION Sender: owner-gann-list@cs.iastate.edu Precedence: bulk Dear Sir, Enclosed, you can find new information for IPMU'96. Could you please send it to the genetic electronic mailing list? With our best wishes, yours sincerely, <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< < IPMU'96 Organization Committee < < Information Processing and Management of Uncertainty < < in Knowledge Based Systems < < Granada, Spain, July 1-5, 1996 < < Fax: +34.58.243317 < < e-mail: ipmu96@robinson.ugr.es < < e-mail for submissions: ipmu96-submissions@robinson.ugr.es < < URL: http://pirata.ugr.es/ipmu96.html < <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< --------- Mail Contribution to the List begin here -------- ----------------------------------------------------------- !!!! NEW INFORMATION FOR IPMU'96 !!!! ----------------------------------------------------------- ***************************************************** * IPMU'96 * * * * Information Processing and Management of * * Uncertainty * * in Knowledge Based Systems * * * * Granada, Spain, July 1-5, 1996 * * * * URL: http://pirata.ugr.es/ipmu96.html * ***************************************************** Dear Colleague, Due to the increasing number of petitions we are receiving these days, the IPMU'96 Organization Committee has decided to postpone the deadlines for submitting. Enclosed you can find the new deadlines, as well as other useful information. ----------------------------------------------------------- INVITED SPEAKERS ----------------------------------------------------------- Prof. T. Terano (Japan). Kampe de Feriet Award Prof. A. F. Rocha (Brazil) Prof. H.J. Zimmermann (Germany) Prof. P. Bonissone (U.S.A.) Prof. R. Scozzafava (Italy) ----------------------------------------------------------- !!!! NEW DEADLINES !!!! ----------------------------------------------------------- December. 1 1995: Deadline for submission of papers. March. 1 1996: Notification of acceptance/rejection. April. 1 1996: Reception of final camera-ready. May 15 1996: Deadline for early registration. July 1-5 1996: CONFERENCE. ----------------------------------------------------------- INSTRUCTIONS ----------------------------------------------------------- There will be a six page (two columns, 10 pt) limit on the final versions of accepted papers. Papers will be carefully reviewed and authors will be notified on the acceptance/rejection by March 1st, 1996. Final camera-ready copies for publication will be required by April 1st, 1996. Authors can submit through two alternative ways: - Sending three copies of each full paper, by surface mail to: IPMU'96 Dpto. Ciencias de la Computacion e Inteligencia Artificial. E.T.S.I. Informatica. Avda. Andalucia, 38 Universidad de Granada. 18071 Granada. Spain. - Sending an electronic mail to: ipmu96-submissions@robinson.ugr.es or alternatively to ipmu96@robinson.ugr.es In this case, the following information must be included (in this order): a) Paper title (plain text) b) Author's names, including professional status. c) Surface mail and e-mail address for a contact author (plain text) d) A short abstract, including keywords or topic indicators (plain text) e) Paper body in postscript format (be sure it is not coded or compressed) ----------------------------------------------------------- TRAVELLING TO GRANADA ----------------------------------------------------------- Granada, a world-famous city, whose history spans over thousand years, also has outstanding features as a modern conference town. The Alhambra, the city's monuments, cultural and University traditions, as well as excellent leisure facilities, good restaurants, lively night life, the Sierra Nevada mountains and the Coast, all attract thousand of visitors to Granada every year. You can visit our city through URL: http://www.pirata.ugr.es/ipmu96.html For accommodation facilities, please contact with the travel agency: Viajes Bonal Avda. de la Constitucion 19 18014 - Granada. Spain Phone: + 34 58 276312 Fax: + 34 58 291967 ----------------------------------------------------------- PAYMENT ----------------------------------------------------------- Transfer to CONGRESO INTERNACIONAL IPMU96. Bank: CAJA GENERAL DE AHORROS DE GRANADA Account: 2031.0234.81.0100058503 Address: Avda. Andalucia s/n. Edificio Samoa 18014 Granada. Spain ----------------------------------------------------------- OTHER USEFUL INFORMATION ----------------------------------------------------------- The frequency of International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems will be increased from the current 4 issues per year to 6 issues, starting from 1996. In recognition of the association between the IPMU community and the journal, the editors of World Scientific Publishing are pleased to inform all the members of the IPMU community, that there is a special subscription rate of US$60 per year for the journal. This special rate remains the same as previous years, despite the increase in frequency. So then, subscribe the journal today! All you need to do is to write/fax in to: World Scientific Publishing Co. Pte. Ltd. Block 1022 Tai Seng Avenue #05-3520 Tai Seng Industrial Estate Singapore 538890 Republic of Singapore Tel: 65-3825663, Fax: 65-3825919 or simply send an email message to any one of the following addresses: worldscp@singnet.com.sg (Singapore office) wsped@singnet.com.sg (Editorial Dept, Singapore) wspmkt@singnet.com.sg (Marketing Dept., Singapore) In any case, please include the acceptance notification of your paper to IPMU'96, or the payment receipt if you are attending to the conference. ----------------------------------------------------------- Announcement of: International Conference on Intelligent Technologies in Human Related Sciences University of Leon, Spain, July 5-7 1996 Please mail to the Organizing Committee: Secretariat of the International Conference on Intelligent Technologies in Human Related Sciences Facultad de CCEE y Empresariales University of Leon Campus de Vergazana, s/n E-24071 Leon, Spain Ph: +34 87 291 742 Fax: +34 87 291 454 From owner-gann-list Thu Nov 2 17:50:14 1995 Received: (from mdomo@localhost) by cs.iastate.edu (8.7.1/8.7.1) id RAA28827 for gann-list-outgoing; Thu, 2 Nov 1995 17:10:40 -0600 (CST) Received: from ren.cs.iastate.edu (ren.cs.iastate.edu [129.186.3.41]) by cs.iastate.edu (8.7.1/8.7.1) with ESMTP id RAA28782 for ; Thu, 2 Nov 1995 17:09:15 -0600 (CST) From: GANN List Admin Received: (from gannadm@localhost) by ren.cs.iastate.edu (8.7.1/8.7.1) id RAA21782 for gann-list@cs.iastate.edu; Thu, 2 Nov 1995 17:09:13 -0600 (CST) Reply-To: mdorigo@ulb.ac.be (Marco DORIGO) X-Originator: mdorigo@ulb.ac.be (Marco DORIGO) X-Sender: mdorigo@134.184.129.6 Message-Id: Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Date: Fri, 27 Oct 1995 16:00:29 +0100 To: neuron@hplabs.hpl.hp.com, gann-list@cs.iastate.edu Subject: Call for Papers: IEEE transactions on Systems, Man, and Cybernetics Sender: owner-gann-list@cs.iastate.edu Precedence: bulk CALL FOR PAPERS (http://iridia.ulb.ac.be/dorigo/ABSI/CFP.html) ADAPTIVE BEHAVIOR Journal Special Issue on COLLECTIVE INTELLIGENCE Guest editors: Jean-Louis Deneubourg, Marco Dorigo Submission Deadline: June 1, 1996. Adaptive Behavior is an international journal published by MIT Press; Editor-in-Chief: Jean-Arcady Meyer, Ecole Normale Superieure, Paris. For this special issue we invite unpublished papers on theoretical or applied research on collective intelligence. Collective intelligence is a property which can be shown by collections of agents which communicate directly or indirectly (by changing some common environment) with each other and which collectively solve problems. Collective intelligence is also sometimes referred to as swarm intelligence. Collective intelligence is a property that can be found in both natural and artificial systems. Authors are therefore encouraged to emphasize the relevance of their research to both natural and artificial systems. Relevant topics for this special issue include (suggestions for further topics are welcome): * Collective robotics, cellular robotic systems, etc. * Distributed problem solving in social insect colonies * Artificial ecologies * Applications to optimization problems Authors intending to submit a manuscript MUST contact the guest editors as soon as possible, and in any case not later than February 15, 1996, to discuss paper ideas and suitability for this issue. Use mdorigo@ulb.ac.be or tel: +32-2-650-3169 or fax: +32-2-650-2715. Submitted papers should be delivered by June 1, 1996. Manuscripts should be typed or laser-printed in English (with American spelling preferred) and double-spaced. Both paper and electronic submission are possible, as described below. Copies of the complete Adaptive Behavior Instructions to Contributors are available on request--also see the Adaptive Behavior journal's home page at http://www.ens.fr:80/bioinfo/www/francais/AB.html For paper submissions, send five (5) copies of submitted papers (hard-copy only) to: Marco Dorigo IRIDIA - CP 194/6 Universite' Libre de Bruxelles Avenue Franklin Roosevelt 50 1050 Bruxelles, Belgium For electronic submissions, use Postscript format, ftp the file to iridia.ulb.ac.be/incoming/AB, and send an email notification to mdorigo@ulb.ac.be Ftp detailed instructions: compress your-paper (both Unix compress and gzip commands are ok) ftp iridia.ulb.ac.be (164.15.11.65) give anonymous as your login name give your e-mail address as password set transmission to binary (just type the command BINARY) cd to /incoming/AB put your-paper send me an email to let me know you transferred the paper Marco Dorigo, Ph.D. IRIDIA Universite' Libre de Bruxelles Avenue Franklin Roosevelt 50 CP 194/6 1050 Bruxelles, Belgium tel. +32-2-6503169 fax +32-2-6502715 mdorigo@ulb.ac.be http://iridia.ulb.ac.be/dorigo/dorigo.html From owner-gann-list Thu Nov 2 17:50:11 1995 Received: (from mdomo@localhost) by cs.iastate.edu (8.7.1/8.7.1) id RAA28927 for gann-list-outgoing; Thu, 2 Nov 1995 17:12:16 -0600 (CST) Received: from ren.cs.iastate.edu (ren.cs.iastate.edu [129.186.3.41]) by cs.iastate.edu (8.7.1/8.7.1) with ESMTP id RAA28922 for ; Thu, 2 Nov 1995 17:12:10 -0600 (CST) From: GANN List Admin Received: (from gannadm@localhost) by ren.cs.iastate.edu (8.7.1/8.7.1) id RAA24017 for gann-list@cs.iastate.edu; Thu, 2 Nov 1995 17:12:06 -0600 (CST) Reply-To: Maja Mataric X-Originator: Maja Mataric Date: Thu, 2 Nov 1995 10:30:37 -0500 Message-Id: <199511021530.KAA14002@garnet.cs.brandeis.edu> To: gann-list@cs.iastate.edu Subject: CFP - Adaptive Behavior Journal Sender: owner-gann-list@cs.iastate.edu Precedence: bulk CALL FOR PAPERS (http://www.cs.brandeis.edu:80/~maja/abj-special-issue/) ADAPTIVE BEHAVIOR Journal Special Issue on COMPLETE AGENT LEARNING IN COMPLEX ENVIRONMENTS Guest editors: Maja J Mataric Submission Deadline: June 1, 1996. Adaptive Behavior is an international journal published by MIT Press; Editor-in-Chief: Jean-Arcady Meyer, Ecole Normale Superieure, Paris. In the last decade, the problems being treated in AI, Alife, and Robotics have witnessed an increase in complexity as the domains under investigation have transitioned from theoretically clean scenarios to more complex dynamic environments. Agents that must adapt in environments such as the physical world, an active ecology or economy, and the World Wide Web, challenge traditional assumptions and approaches to learning. As a consequence, novel methods for automated adaptation, action selection, and new behavior acquisition have become the focus of much research in the field. This special issue of Adaptive Behavior will focus on situated agent learning in challenging environments that feature noise, uncertainty, and complex dynamics. We are soliciting papers describing finished work on autonomous learning and adaptation during the lifetime of a complete agent situated in a dynamic environment. We encourage submissions that address several of the following topics within a whole agent learning system: * learning from ambiguous perceptual inputs * learning with noisy/uncertain action/motor outputs * learning from sparse, irregular, inconsistent, and noisy reinforcement/feedback * learning in real time * combining built-in and learned knowledge * learning in complex environments requiring generalization in state representation * learning from incremental and delayed feedback * learning in smoothly or discontinuously changing environments We invite submissions from all areas in AI, Alife, and Robotics that treat either complete synthetic systems or models of biological adaptive systems situated in complex environments. Submitted papers should be delivered by June 1, 1996. Authors intending to submit a manuscript should contact the guest editor as soon as possible to discuss paper ideas and suitability for this issue. Use maja@cs.brandeis.edu or tel: (617) 736-2708 or fax: (617) 736-2741. Manuscripts should be typed or laser-printed in English (with American spelling preferred) and double-spaced. Both paper and electronic submission are possible, as described below. Copies of the complete Adaptive Behavior Instructions to Contributors are available on request--also see the Adaptive Behavior journal's home page at: http://www.ens.fr:80/bioinfo/www/francais/AB.html. For paper submissions, send five (5) copies of submitted papers (hard-copy only) to: Maja Mataric Volen Center for Complex Systems Computer Science Department Brandeis University Waltham, MA 02254-9110, USA For electronic submissions, use Postscript format, ftp the file to ftp.cs.brandeis.edu/incoming, and send an email notification to maja@cs.brandeis.edu. For a Web page of this call, and detailed ftp directions, see: http://www.cs.brandeis.edu/~maja/abj-special-issue/ end{document} From owner-gann-list Thu Nov 2 17:50:08 1995 Received: (from mdomo@localhost) by cs.iastate.edu (8.7.1/8.7.1) id RAA28973 for gann-list-outgoing; Thu, 2 Nov 1995 17:13:35 -0600 (CST) Received: from ren.cs.iastate.edu (ren.cs.iastate.edu [129.186.3.41]) by cs.iastate.edu (8.7.1/8.7.1) with ESMTP id RAA28815 for ; Thu, 2 Nov 1995 17:10:07 -0600 (CST) From: GANN List Admin Received: (from gannadm@localhost) by ren.cs.iastate.edu (8.7.1/8.7.1) id RAA22542 for gann-list@cs.iastate.edu; Thu, 2 Nov 1995 17:10:04 -0600 (CST) Reply-To: Evolutionary Computing X-Originator: Evolutionary Computing Mon, 30 Oct 1995 19:57:51 +0000 Date: Mon, 30 Oct 1995 21:20:05 +0200 (EET) To: announcement-list , bengio@iro.umontreal.ca, bersini@ulb.ac.be, bonarini@ipmel2.elet.polimi.it, braun@ira.uka.de, dirk.thierens@esat.kuleuven.ac.be, dorne@eerie.fr, gseront@ulb.ac.be, hao@eerie.fr, jakob@informatik.uni-erlangen.de, jarabas@ipe.pw.edu.pl, jml@ipe.pw.edu.pl, klawonn@ibr.cs.tu-bs.de, maniezzo@ipmel2.elet.polimi.it, muehlen@gmd.de, patel@ipmel2.elet.polimi.it, piola@di.unito.it, rose@itp02.physik.hu-berlin.de, saitta@di.unito.it, schuch@itp02.physik.hu-berlin.de, slangerm@ulb.ac.be, voigt@fb10.tu-berlin.de, werner@itp02.physik.hu-berlin.de, williabv@cs.aston.ac.uk, zhang@gmd.de Cc: ROSYCS EvoSection - Committee , dave@reading.ac.uk, gusz@WI.leidenuniv.nl, joe@gonzo.informatik.uni-dortmund.de, manderick@cs.few.eur.nl, martin@virginia.edu, meyer@wotan.ens.fr, tcf@btc.uwe.ac.uk, zbyszek@uncc.edu, liste-evol , cells@tce.ing.uniroma1.it, EP-List@magenta.me.fau.edu, evolutionary-computing@mailbase.ac.uk, ga-molecule-approval@interval.com, gann-list@cs.iastate.edu Subject: ROSYCS '96 - Evolutionary Computing Section Message-Id: Mime-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-gann-list@cs.iastate.edu Precedence: bulk _________________________________________________________________________________________________ The Evolutionary Computing Section of ROSYCS '96 Call for papers The Faculty of Computer Science of The "Al.I.Cuza" University of Iasi organises the 10th Romanian Symposium on Computer Science - formerly, 1977 - 1991, INFO-IASI. The symposium will be held in Iasi, May 30th to June 1st 1996. Our symposium will continue its tradition of emphasising theoretical aspects of Computer Science. Topics of interest for our symposium include: *Computability and Complexity *Parallel and Distributed Computing *Formal Languages *Artificial Intelligence *Graph Theory *Natural Language Processing *Databases *Logic Programming *Computer Optimisation & Applied Mathematics The 1996 edition will have two special sections dedicated to important fields in contemporary Computer Science: EVOLUTIONARY COMPUTING and CONCURRENT SYSTEMS AND FORMAL LANGUAGES. Leading personalities of these fields will give invited talks for the special sessions. The invited talks will be announced shortly. The official language of ROSYCS '96 will be English. The Evolutionary Computing section will be dedicated to both theoretical results and applications of Genetic Algorithms, Evolution Strategies and Evolutionary Programming; contributions in Genetic Programming and Classifier Systems are welcomed. SCIENTIFIC COMMITTEE of ROSYCS '96 ('EC' - EVOLUTIONARY COMPUTING SECTION): Peter Barclay - Napier University, Edinburgh, UK Virgil Emil Cazanescu - Bucharest University Dan Cristea -"Al.I.Cuza" University, Iasi Cornelius Croitoru - "Al.I.Cuza" University, Iasi Gusz Eiben - Leiden University, The Netherland (EC) Victor Felea - "Al.I.Cuza" University, Iasi Militon Frentiu - "Babes-Bolyai" University, Cluj-Napoca Terence Fogarty - University of West England, Bristol, UK (EC) Gheorghe Grigoras - "Al.I.Cuza" University, Iasi Calin Ignat - "Al.I.Cuza" University, Iasi Toader Jucan - "Al.I.Cuza" University, Iasi (chair) Henri Luchian - "Al.I.Cuza" University, Iasi (co-chair for the Evolutionary Computing section) Dorel Lucanu - "Al.I.Cuza" University, Iasi Bernard Manderick - Free University, Brussels, Belgium (EC) Worthy Martin - University of Virginia, Charlottesville, USA (EC) Stefan Maruster - University of Timisoara Cristian Masalagiu - "Al.I.Cuza" University, Iasi Ito Masimoto - University of Kyoto, Japan Jean-Arcady Meyer - Ecole Normale Superieure, Paris, France (EC) Zbigniew Michalewicz - University of North Carolina, Charlotte, USA (EC) Grigor Moldovan - "Babes-Bolyai" University - Cluj-Napoca Nicolas Nicolov - University of Edinburgh, UK Ben Paechter - Napier University, Edinburgh, UK (EC) Gheorghe Paun - University of Bucharest Arto Salomaa - University of Turku, Finland Joachim Sprave - University of Dortmund, Germany (EC) Gheorghe Stefanescu - University of Bucharest Ioan Tomescu - University of Bucharest Nicolae Tandareanu - University of Craiova Leon Tambulea - "Babes-Bolyai" University, Cluj-Napoca Ferucio Tiplea - "Al.I.Cuza" University, Iasi Ion Vaduva - University of Bucharest SUBMISSIONS Prospective authors are invited to submit papers in the domains of interest for ROSYCS, in English. Three (3) copies of each paper will be sent for review. The papers should not exceed 12 pages. A separate title page will contain the title, all authors' names and complete addresses, keywords, the abstract; the fax number, e-mail and surface mail addresses for correspondence will also appear on this page. E-mail submissions of (plain text) title pages are encouraged. The e-mail address of the symposium is : rosycs@cs.cccis.sfos.ro For the special section on Evolutionary Computing, the e-mail address is: evol@cccis.sfos.ro Surface mail submissions and all correspondence will be sent to : MS. EUGENIA COTOFREI SECRETARY OF ROSYCS '96 FACULTY OF COMPUTER SCIENCE "AL.I.CUZA" UNIVERSITY IASI - 6600 ROMANIA Instructions for camera-ready versions will be given in the second announcement. IMPORTANT DATES: Deadline for the submission of papers ................. - January 31, 1996 Notification of acceptance............................. - March 20, 1996 Camera ready versions ................................. - April 20, 1996 Symposium days ........................................ - May 30 - June 1, 1996 FEES. The registration fee is $100. Registration fee includes the proceedings volume of the symposium (available during the congress), a welcome event, the symposium party, refreshments and excursion. For Romanian participants the fee is ROL 50000. A limited number of student registrations will be assigned, subject to applications review. Applicants should send to the address above an application letter and a statement of research interests. ABOUT IASI. Iasi is considered to be the cultural capital town of Romania. The 7 higher education institutions, among which the "Al.I.Cuza" University, have over 45,000 students in a town of some 400,000 inhabitants. A branch of the Romanian Academy, which includes an Institute for Theoretical Computer Science, and several other research institutes in chemistry, physics, engineering, agricultural sciences shape the scientific life of the town. The "Alecsandri" National Theatre, the Opera, the "Moldova" Philharmonic, the "Morning-Star" Theatre, numerous museums (arts, history, ethnography, natural sciences, literature, sound, etc.), memorial houses of outstanding Romanian writers and artists, public libraries, publishing houses display an expanding cultural life. Located on seven hills, the town offers wonderful views from each of them. Not far away from Iasi one can visit the famous Bucovina monasteries, Neamt monasteries, and Cotnari vineyards. Iasi is located at 400 km from Bucharest. Iasi can be reached by either plane (one-hour flights, twice a week-day, from Bucharest), train (5-hour journey, 6 speed trains and one Intercity service from Bucharest daily; 4 speed services from Timisoara and Cluj daily) or car (two motor-ways from Bucharest - where Hertz and other car-renting services are available at the international airport; one motor-way from Cluj-Suceava, with further connections to Hungary and Ukraine-Poland). PLEASE FILL IN AND (E-)MAIL THE FORM BELLOW: TITLE AND NAME: AFFILIATION: |__| I INTEND TO SUBMIT A PAPER TO ROSYCS '96 TENTATIVE TITLE: |__| I INTEND TO ATTEND ROSYCS '96 |__| I HAVE THE FOLLOWING SUGGESTIONS FOR THE ORGANISERS: From owner-gann-list Fri Nov 10 14:54:02 1995 Received: (from mdomo@localhost) by cs.iastate.edu (8.7.1/8.7.1) id OAA13582 for gann-list-outgoing; Fri, 10 Nov 1995 14:23:30 -0600 (CST) Received: from ren.cs.iastate.edu (ren.cs.iastate.edu [129.186.3.41]) by cs.iastate.edu (8.7.1/8.7.1) with ESMTP id OAA13575 for ; Fri, 10 Nov 1995 14:23:19 -0600 (CST) From: GANN List Admin Received: (from gannadm@localhost) by ren.cs.iastate.edu (8.7.1/8.7.1) id OAA10260 for gann-list@cs.iastate.edu; Fri, 10 Nov 1995 14:23:17 -0600 (CST) Reply-To: bs@neuroinformatik.ruhr-uni-bochum.de (Bernhard Sendhoff) X-Originator: bs@neuroinformatik.ruhr-uni-bochum.de (Bernhard Sendhoff) Message-Id: <199511100822.JAA22075@kol.neuroinformatik.ruhr-uni-bochum.de> Subject: ICANN 96 ANNOUNCEMENT To: gann-list@cs.iastate.edu Date: Fri, 10 Nov 1995 09:22:06 +0100 (MET) X-Mailer: ELM [version 2.4 PL23] Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-gann-list@cs.iastate.edu Precedence: bulk ***************************************************** ** ** ** I C A N N 1 9 9 6 ** ** ** ** International Conference ** ** on ** ** Artificial Neural Networks ** ** 1996 ** ** ** ***************************************************** ** ** ** 1st CALL FOR PAPERS ** ** ** ***************************************************** ** ** ** Information on the World-Wide-Web ** ** http://www.neuroinformatik.ruhr-uni-bochum.de/ ** ** icann96/ ** ** ** ***************************************************** The International Conference on Artificial Neural Networks 1996 sponsored by the European Neural Network Society, continues the successful series begun in Helsinki (1991), which has become the premier meeting of the European scientific community interested in the design, development and application of natural and artificial neural networks. In 1996, the venue will be at the University of Bochum, Germany and the conference will be hosted by the Institut fuer Neuroinformatik. ***************************** * Important dates * ***************************** Submission of papers: 3 March 1996 Submission of camera-ready copy: 13 May 1996 Proposals for tutorials: 15 January 1996 Submission of papers related, but not limited, to the following topics are invited Theory ------------------------ (e.g., algorithms & architectures, learning, self-organizing networks, dynamical systems) Applications ------------------------ (e.g., data analysis, process control, robotics, optimization & prediction) Sensory processing ------------------------ (e.g., image & sound analysis, sensory integration) Cognitive science and AI ------------------------ (e.g., modeling in psychology & psychophysics, integration of neural & symbolic processing) Implementations ------------------------ (e.g., software, parallel, digital & analog VLSI, optical) Neurobiology ------------------------ (e.g., dynamics of single neurons, self-organization, cortex modelling, sensory-motor integration) Papers must be received by March 1996. Papers received after that date will be returned unopened. All submissions will be acknowledged by post or electronic mail. Five copies (one original and four copies) of the paper must be submitted. Four pages are encouraged; however, the paper must not exceed six pages,including figures, tables and references. It should be written in English on A4 paper, in a Roman font at least 10 and preferable 12 point in size, without page numbers. If possible, please make use of the Latex style file available via e-mail. Indicate in the accompanying letter the topical area into which the paper fits best, presentation preferred (oral or poster), and the corresponding author (name, postal and e-mail address, telephone and fax numbers). All submissions will be reviewed double-blind by researchers in the field, and authors will be notified of the decision by 15 April 1996. A limited number of papers will be accepted for oral and poster presentations. Accepted papers can be revised and must be received in camera-ready form by 13 May 1996. Arrangements are being made to publish the proceedings in the Lecture Notes on Computer Science series of Springer Verlag, and will likely include an on-line version that will be available to registered conference participants well before the conference date. ***************************** * Tutorials * ***************************** The conference will be preceeded by a a day of tutorials. These will cover such topics as future development in neural networks, new approaches to learning, non-linear dynamics, industrial applications of neural network approaches, practical experiences with neural hardware, applying growing cell structures, and more. Proposals are solicited and should be submitted to the Tutorials Chair by 15 January 1996. ****************************** * Conference secretariat * ****************************** ICANN 96 Secretariat Institut fuer Neuroinformatik, ND 03/34 Ruhr-Universitaet Bochum 44780 Bochum, Germany Phone: +49 234 700 7997 Fax: +49 234 7094 210 icann96@neuroinformatik.ruhr-uni-bochum.de ***************************** * Program Co-Chairs * ***************************** Prof. Werner von Seelen Prof. Christoph von der Malsburg Institut fuer Neuroinformatik, ND 03/34 Ruhr-Universitaet Bochum 44780 Bochum, Germany icann96@neuroinformatik.ruhr-uni-bochum.de ***************************** * Tutorials Chair * ***************************** Dr. Joerg Kopecz Zentrum fuer Neuroinformatik GmbH Universitaetsstr. 160 44801 Bochum, Germany kopecz@zn.ruhr-uni-bochum.de ***************************** * Publications Chair * ***************************** Dr. Jan Vorbrueggen Institut fuer Neuroinformatik, ND 03/34 Ruhr-Universitaet Bochum 44780 Bochum, Germany jan@neuroinformatik.ruhr-uni-bochum.de ----------------------------------------------------------------------------- Bernhard Sendhoff Institut fuer Neuroinformatik Ruhr-Universitaet Bochum 44780 Bochum Germany Fon: ++49 (0)234 7005558 Fax: ++49 (0)234 7094209 WWW: http://www.neuroinformatik.ruhr-uni-bochum.de eM : bs@neuroinformatik.ruhr-uni-bochum.de From owner-gann-list Fri Nov 10 14:54:08 1995 Received: (from mdomo@localhost) by cs.iastate.edu (8.7.1/8.7.1) id OAA13540 for gann-list-outgoing; Fri, 10 Nov 1995 14:22:27 -0600 (CST) Received: from ren.cs.iastate.edu (ren.cs.iastate.edu [129.186.3.41]) by cs.iastate.edu (8.7.1/8.7.1) with ESMTP id OAA13532 for ; Fri, 10 Nov 1995 14:22:18 -0600 (CST) From: GANN List Admin Received: (from gannadm@localhost) by ren.cs.iastate.edu (8.7.1/8.7.1) id OAA09384 for gann-list@cs.iastate.edu; Fri, 10 Nov 1995 14:22:16 -0600 (CST) Reply-To: oldair@octans.ele.puc-rio.br (Oldair Ferreira G. de Brito) X-Originator: oldair@octans.ele.puc-rio.br (Oldair Ferreira G. de Brito) Date: Fri, 27 Oct 1995 14:23:01 +0300 Message-Id: <9510271623.AA01262@valsa.puc-rio.br> To: gann-list@cs.iastate.edu Subject: Tariffs for Electricity Supply Sender: owner-gann-list@cs.iastate.edu Precedence: bulk Pontificia Universidade Catolica do Rio de Janeiro PUC-RIO Here at Dept. of Electrical Engineering of PUC, Rio de Janeiro, we are developing projects on Artificial Intelligence area (Neural Network, Genetic Algorithm, Expert System and Fuzzy Logic). I am looking for any reference on Genetic Algorithms, Fuzzy Logic and Neural area. I would appreciate any tip on this. Thanking you in advance, sincerely yours, ============================================================================== Karla Tereza Figueiredo ICA: Nucleo de Pesquisa em Inteligencia Computacional Aplicada Dept. de Engenharia Eletrica, PUC-RIO R. Marques de Sao Vicente, 225 - Gavea CXP 38063 fax: +55 (0)21 511 5154 CEP 22453-900 - Rio de Janeiro - RJ - Brasil tel: +55 (0)21 529 9433 http://www.ele.puc-rio.br/~karla/ e-mail: karla@ele.puc-rio.br ============================================================================== From owner-gann-list Fri Nov 10 14:54:06 1995 Received: (from mdomo@localhost) by cs.iastate.edu (8.7.1/8.7.1) id OAA13567 for gann-list-outgoing; Fri, 10 Nov 1995 14:23:02 -0600 (CST) Received: from ren.cs.iastate.edu (ren.cs.iastate.edu [129.186.3.41]) by cs.iastate.edu (8.7.1/8.7.1) with ESMTP id OAA13553 for ; Fri, 10 Nov 1995 14:22:49 -0600 (CST) From: GANN List Admin Received: (from gannadm@localhost) by ren.cs.iastate.edu (8.7.1/8.7.1) id OAA09498 for gann-list@cs.iastate.edu; Fri, 10 Nov 1995 14:22:46 -0600 (CST) Reply-To: costa@ele.puc-rio.br (Rodrigo M. L. A. Costa [93.1]) X-Originator: costa@ele.puc-rio.br (Rodrigo M. L. A. Costa [93.1]) Date: Tue, 7 Nov 95 18:10:22 EDT Message-Id: <9511072010.AA20766@Octans.ele.puc-rio.br> To: gann-list@cs.iastate.edu Subject: REFERENCES IN INTELLIGENT SYSTEMS IN FINANCES Cc: genetic-programming@CS.Stanford.EDU, intcon@phoenix.ee.unsw.edu.au, neuron@CATTELL20.psych.upenn.edu Sender: owner-gann-list@cs.iastate.edu Precedence: bulk REFERENCES IN INTELLIGENT SYSTEMS IN FINANCES I am a Master Degree student from ICA (Research Centre of Applied Computacional Intelligence) at the Electrical Engineering Department (PUC-Rio) and I am looking for information about Intelligent Systems (Neural Networks, Fuzzy Logic, Genetic Algorithms) in Finance (specifically Credit Assessment and Insurance). Any help will be appreciated : ftp sites, mailing lists, WWW sites, papers or any other kind of references. Thanks in advance, Rodrigo (costa@ele.puc-rio.br) From owner-gann-list Wed Nov 15 19:26:58 1995 Received: (from mdomo@localhost) by cs.iastate.edu (8.7.1/8.7.1) id SAA17477 for gann-list-outgoing; Wed, 15 Nov 1995 18:56:03 -0600 (CST) Received: from ren.cs.iastate.edu (ren.cs.iastate.edu [129.186.3.41]) by cs.iastate.edu (8.7.1/8.7.1) with ESMTP id SAA17472 for ; Wed, 15 Nov 1995 18:55:59 -0600 (CST) From: GANN List Admin Received: (from gannadm@localhost) by ren.cs.iastate.edu (8.7.1/8.7.1) id SAA11677 for gann-list@cs.iastate.edu; Wed, 15 Nov 1995 18:55:58 -0600 (CST) Reply-To: qin@autom.fpms.ac.be (Qin Liang) X-Originator: qin@autom.fpms.ac.be (Qin Liang) with TCP; Wed, 15 Nov 95 16:33:12 +0100 Date: Wed, 15 Nov 1995 16:39:49 GMT Message-Id: <199511151639.QAA24982@autom.fpms.ac.be> To: gann-list@cs.iastate.edu Subject: Neural Network Software X-Sun-Charset: US-ASCII Sender: owner-gann-list@cs.iastate.edu Precedence: bulk Dear Colleagues, last few years. We are going to gather information on Neural Network software that have been used in different fields. If you are involved somehow in developing or using Neural Network software, we appreciate the information on existing software, such as name of the software, neural netwok models implemented, performance comparisons, advantages and disadvantages and ftp-site. Once the sufficient information is received, we will compile a survey for the list. Sincerely yours, ======================================================================== _/ LIANG Qin _/ _/ Laboratoire d'Automatique _/ Faculte Polytechnique de Mons _/ Boulevard Dolez, 31 _/ _/ B-7000 Mons _/_/_/_/ Belgium E-Mail: qin@autom.fpms.ac.be ======================================================================== From owner-gann-list Fri Nov 17 12:30:43 1995 Received: (from mdomo@localhost) by cs.iastate.edu (8.7.1/8.7.1) id MAA05260 for gann-list-outgoing; Fri, 17 Nov 1995 12:09:01 -0600 (CST) Received: from ren.cs.iastate.edu (ren.cs.iastate.edu [129.186.3.41]) by cs.iastate.edu (8.7.1/8.7.1) with ESMTP id MAA05255 for ; Fri, 17 Nov 1995 12:08:56 -0600 (CST) From: GANN List Admin Received: (from gannadm@localhost) by ren.cs.iastate.edu (8.7.1/8.7.1) id MAA21564 for gann-list@cs.iastate.edu; Fri, 17 Nov 1995 12:08:54 -0600 (CST) Reply-To: robert@fit.qut.edu.au (Robert Andrews) X-Originator: robert@fit.qut.edu.au (Robert Andrews) Date: Fri, 17 Nov 1995 13:28:24 +1000 (EST) Message-Id: <199511170328.NAA11516@ocean.fit.qut.edu.au> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" To: gannadm@cs.iastate.edu X-Mailer: Sender: owner-gann-list@cs.iastate.edu Precedence: bulk ============================================================= FIRST CALL FOR PAPERS AISB-96 WORKSHOP Society for the Study of Artificial Intelligence and Simulation of Behaviour (SSAISB) University of Sussex, Brighton, England April 2, 1996 -------------------------------------------- RULE-EXTRACTION FROM TRAINED NEURAL NETWORKS -------------------------------------------- Robert Andrews Neurocomputing Research Centre Queensland University of Technology Brisbane 4001 Queensland, Australia Phone: +61 7 864-1656 Fax: +61 7 864-1969 E-mail: robert@fit.qut.edu.au Joachim Diederich Neurocomputing Research Centre Queensland University of Technology Brisbane 4001 Queensland, Australia Phone: +61 7 864-2143 Fax: +61 7 864-1801 E-mail: joachim@fit.qut.edu.au Lee Giles NEC Research Institute 4 Independence Way Princeton, NJ 08540 The objective of the workshop is to provide a discussion platform for researchers interested in Artificial Neural Networks (ANNs), Artificial Intelligence (AI) and Cognitive Science. The workshop should be of considerable interest to computer scientists and engineers as well as to cognitive scientists and people interested in ANN applications which require a justification of a classification or inference. INTRODUCTION It is becoming increasingly apparent that without some form of explanation capability, the full potential of trained Artificial Neural Networks may not be realised. The problem is an inherent inability to explain in a comprehensible form, the process by which a given decision or output generated by an ANN has been reached. For Artificial Neural Networks to gain a even wider degree of user acceptance and to enhance their overall utility as learning and generalisation tools, it is highly desirable if not essential that an `explanation' capability becomes an integral part of the functionality of a trained ANN. Such a requirement is mandatory if, for example, the ANN is to be used in what are termed as `safety critical' applications such as airlines and power stations. In these cases it is imperative that a system user be able to validate the output of the Artificial Neural Network under all possible input conditions. Further the system user should be provided with the capability to determine the set of conditions under which an output unit within an ANN is active and when it is not, thereby providing some degree of transparency of the ANN solution. Craven & Shavlik (1994) define the rule-extraction from neural networks task as follows: "Given a trained neural network and the examples used to train it, produce a concise and accurate symbolic description of the network." The following discussion of the importance of rule-extraction algorithms is based on this definition. THE IMPORTANCE OF RULE-EXTRACTION ALGORITHMS Since rule extraction from trained Artificial Neural Networks comes at a cost in terms of resources and additional effort, an early imperative in any discussion is to delineate the reasons why rule extraction is an important, if not mandatory, extension of conventional ANN techniques. The merits of including rule extraction techniques as an adjunct to conventional Artificial Neural Network techniques include: Data exploration and the induction of scientific theories Over time neural networks have proven to be extremely powerful tools for data exploration with the capability to discover previously unknown dependencies and relationships in data sets. As Craven and Shavlik (1994) observe, `a (learning) system may discover salient features in the input data whose importance was not previously recognised.' However, even if a trained Artificial Neural Network has learned interesting and possibly non-linear relationships, these relationships are encoded incomprehensibly as weight vectors within the trained ANN and hence cannot easily serve the generation of scientific theories. Rule-extraction algorithms significantly enhance the capabilities of ANNs to explore data to the benefit of the user. Provision of a `user explanation' capability Experience has shown that an explanation capability is considered to be one of the most important functions provided by symbolic AI systems. In particular, the salutary lesson from the introduction and operation of Knowledge Based systems is that the ability to generate even limited explanations (in terms of being meaningful and coherent) is absolutely crucial for the user-acceptance of such systems. In contrast to symbolic AI systems, Artificial Neural Networks have no explicit declarative knowledge representation. Therefore they have considerable difficulty in generating the required explanation structures. It is becoming increasingly apparent that the absence of an `explanation' capability in ANN systems limits the realisation of the full potential of such systems and it is this precise deficiency that the rule extraction process seeks to redress. Improving the generalisation of ANN solutions Where a limited or unrepresentative data set from the problem domain has been used in the ANN training process, it is difficult to determine when generalisation can fail even with evaluation methods such as cross-validation. By being able to express the knowledge embedded within the trained Artificial Neural Network as a set of symbolic rules, the rule-extraction process may provide an experienced system user with the capability to anticipate or predict a set of circumstances under which generalisation failure can occur. Alternatively the system user may be able to use the extracted rules to identify regions in input space which are not represented sufficiently in the existing ANN training set data and to supplement the data set accordingly. A CLASSIFICATION SCHEME FOR RULE EXTRACTION ALGORITHMS The method of classification proposed here is in terms of: (a) the expressive power of the extracted rules; (b) the `translucency' of the view taken within the rule extraction technique of the underlying Artificial Neural Network units; (c) the extent to which the underlying ANN incorporates specialised training regimes; (d) the `quality' of the extracted rules; and (e) the algorithmic `complexity' of the rule extraction/rule refinement technique. The `translucency' dimension of classification is of particular interest. It is designed to reveal the relationship between the extracted rules and the internal architecture of the trained ANN. It comprises two basic categories of rule extraction techniques viz `decompositional' and `pedagogical' and a third - labelled as `eclectic' - which combines elements of the two basic categories. The distinguishing characteristic of the `decompositional' approach is that the focus is on extracting rules at the level of individual (hidden and output) units within the trained Artificial Neural Network. Hence the `view' of the underlying trained Artificial Neural Network is one of `transparency'. The translucency dimension - `pedagogical' is given to those rule extraction techniques which treat the trained ANN as a `black box' ie the view of the underlying trained Artificial Neural Network is `opaque'. The core idea in the `pedagogical' approach is to `view rule extraction as a learning task where the target concept is the function computed by the network and the input features are simply the network's input features'. Hence the `pedagogical' techniques aim to extract rules that map inputs directly into outputs. Where such techniques are used in conjunction with a symbolic learning algorithm, the basic motif is to use the trained Artificial Neural Network to generate examples for the learning algorithm. As indicated above the proposed third category in this classification scheme are composites which incorporate elements of both the `decompositional' and `pedagogical' (or `black-box') rule extraction techniques. This is the `eclectic' group. Membership in this category is assigned to techniques which utilise knowledge about the internal architecture and/or weight vectors in the trained Artificial Neural Network to complement a symbolic learning algorithm. An ancillary problem to that of rule extraction from trained ANNs is that of using the ANN for the `refinement' of existing rules within symbolic knowledge bases. The goal in rule refinement is to use a combination of ANN learning and rule extraction techniques to produce a `better' (ie a `refined') set of symbolic rules which can then be applied back in the original problem domain. In the rule refinement process, the initial rule base (ie what may be termed `prior knowledge') is inserted into an ANN by programming some of the weights. The rule refinement process then proceeds in the same way as normal rule extraction viz (1) train the network on the available data set(s); and (2) extract (in this case the `refined') rules - with the proviso that the rule refinement process may involve a number of iterations of the training phase rather than a single pass. DISCUSSION POINTS FOR WORKSHOP PARTICIPANTS 1. Decompositional vs. learning approaches to rule- extraction from ANNs - What are the advantages and disadvantages w.r.t. performance, solution time, computational complexity, problem domain etc. Are decompositional approaches always dependent on a certain ANN architecture? 2. Rule-extraction from trained neural networks vs. symbolic induction. What are the relative strength and weaknesses? 3. What are the most important criteria for rule quality? 4. What are the most suitable representation languages for extracted rules? How does the extraction problem vary across different languages? 5. What is the relationship between rule-initialisation (insertion) and rule-extraction? For instance, are these equivalent or complementary processes? How important is rule-refinement by neural networks? 6. Rule-extraction from trained neural networks and computational learning theory. Is generating a minimal rule-set which mimics an ANN a hard problem? 7. Does rule-initialisation result in faster learning and improved generalisation? 8. To what extent are existing extraction algorithms limited in their applicability? How can these limitations be addressed? 9. Are there any interesting rule-extraction success stories? That is, problem domains in which the application of rule-extraction methods has resulted in an interesting or significant advance. ACKNOWLEDGEMENT Many thanks to Mark Craven, and Alan Tickle for comments on earlier versions of this proposal. RELEVANT PUBLICATIONS Andrews, R Diederich, J and Tickle, A.B.: A survey and critique of techniques for extracting rules from trained artificial neural networks. To appear: Knowledge-Based Systems, 1995 (ftp:fit.qut.edu.au//pub/NRC/ps/QUTNRC-95-01- 02.ps.Z) Andrews, R and Geva, S: `Rule extraction from a constrained error back propagation MLP' Proc. 5th Australian Conference on Neural Networks Brisbane Queensland (1994) pp 9-12 Andrews, R and Geva, S `Inserting and extracting knowledge from constrained error back propagation networks' Proc. 6th Australian Conference on Neural Networks Sydney NSW (1995) Craven, M W and Shavlik , J W `Using sampling and queries to extract rules from trained neural networks' Machine Learning: Proceedings of the Eleventh International Conference (San Francisco CA) (1994) (in print) Diederich, J `Explanation and artificial neural networks' International Journal of Man-Machine Studies Vol 37 (1992) pp 335-357 Fu, L M `Neural networks in computer intelligence' McGraw Hill (New York) (1994) Fu, L M `Rule generation from neural networks' IEEE Transactions on Systems, Man, and Cybernetics Vol 28 No 8 (1994) pp 1114-1124 Gallant, S `Connectionist expert systems' Communications of the ACM Vol 31 No 2 (February 1988) pp 152-169 Giles, C L and Omlin C W `Rule refinement with recurrent neural networks' Proc. of the IEEE International Conference on Neural Networks (San Francisco CA) (March 1993) pp 801-806 Giles, C L and Omlin C W `Extraction, insertion, and refinement of symbolic rules in dynamically driven recurrent networks' Connection Science Vol 5 Nos 3 and 4 (1993) pp 307-328 Giles, C L, Miller, C B, Chen, D, Chen, H, Sun, G Z and Lee, Y C `Learning and extracting finite state automata with second-order recurrent neural networks' Neural Computation Vol 4 (1992) pp 393-405 Hayward, R.; Pop, E.; Diederich, J.: Extracting Rules for Grammar Recognition from Cascade-2 Networks. Proceeding, IJCAI-95 Workshop on Machine Learning and Natural Language Processing. McMillan, C, Mozer, M C and Smolensky, P `The connectionist scientist game: rule extraction and refinement in a neural network' Proc. of the Thirteenth Annual Conference of the Cognitive Science Society (Hillsdale NJ) 1991 Omlin, C W, Giles, C L and Miller, C B `Heuristics for the extraction of rules from discrete time recurrent neural networks' Proc. of the International Joint Conference on Neural Networks (IJCNN'92) (Baltimore MD) Vol 1 (1992) pp 33 Pop, E, Hayward, R, and Diederich, J `RULENEG: extracting rules from a trained ANN by stepwise negation' QUT NRC (December 1994) Sestito, S and Dillon, T `Automated knowledge acquisition of rules with continuously valued attributes' Proc. 12th International Conference on Expert Systems and their Applications (AVIGNON'92) (Avignon France) (May 1992) pp 645-656. Sestito, S and Dillon, T `Automated knowledge acquisition' Prentice Hall (Australia) (1994) Artificial Neural Networks' Technical Report IAI-TR-93-5 Institut fur Informatik III Universitat Bonn (1994) Tickle, A B, Orlowski, M, and Diederich, J `DEDEC: decision detection by rule extraction from neural networks' QUT NRC (September 1994) Towell, G and Shavlik, J `The Extraction of Refined Rules Tresp, V, Hollatz, J and Ahmad, S `Network Structuring and Training Using Rule-based Knowledge' Advances In Neural Information Processing Vol 5 (1993) pp871-878 SUBMISSION OF WORKSHOP EXTENDED ABSTRACTS/PAPERS Authors are invited to submit 3 copies of either an extended abstract or full paper relating to one of the topic areas listed above. Papers should be written in English in single column format and should be limited to no more than eight, (8) sides of A4 paper including figures and references. Centered at the top of the first page should be complete title, author name(s), affiliation(s), and mailing and email address(es), followed by blank space, abstract(15-20 lines), and text. Please include the following information in an accompanying cover letter: Full title of paper, presenting author's name, address, and telephone and fax numbers, authors e-mail address. Submission Deadline is January 15th,1996 with notification to authors by 31st January,1996. For further information, inquiries, and paper submissions please contact: Robert Andrews Queensland University of Technology GPO Box 2434 Brisbane Q. 4001. Australia. phone +61 7 864-1656 fax +61 7 864-1969 email robert@fit.qut.edu.au More information about the AISB-96 workshop series is available from: ftp: ftp.cogs.susx.ac.uk pub/aisb/aisb96 WWW: http://www.cogs.susx.ac.uk/aisb/aisb96/CFP/rule_extraction.html WORKSHOP PARTICIPATION CHARGES The workshop fees are listed below. Note that these fees include lunch. Student charges are shown in brackets. AISB NON-ASIB MEMBERS MEMBERS 1 Day Workshop 65 (45) 80 LATE REGISTRATION: 85 (60) 100 PROGRAM COMMITTEE MEMBERS R. Andrews, Queensland University of Technology A. Tickle, Queensland University of Technology S. Sestito, DSTO, Australia J. Shavlik, University of Wisconsin From owner-gann-list Fri Nov 17 12:30:52 1995 Received: (from mdomo@localhost) by cs.iastate.edu (8.7.1/8.7.1) id MAA05223 for gann-list-outgoing; Fri, 17 Nov 1995 12:08:11 -0600 (CST) Received: from ren.cs.iastate.edu (ren.cs.iastate.edu [129.186.3.41]) by cs.iastate.edu (8.7.1/8.7.1) with ESMTP id MAA05217 for ; Fri, 17 Nov 1995 12:08:08 -0600 (CST) From: GANN List Admin Received: (from gannadm@localhost) by ren.cs.iastate.edu (8.7.1/8.7.1) id MAA19845 for gann-list@cs.iastate.edu; Fri, 17 Nov 1995 12:08:05 -0600 (CST) Reply-To: John Koza X-Originator: John Koza Posted-Date: Thu, 16 Nov 1995 06:34:23 -0800 (PST) Date: Thu, 16 Nov 95 6:34:23 PST To: gann-list@cs.iastate.edu Subject: Final GP-96 CFP Message-ID: Sender: owner-gann-list@cs.iastate.edu Precedence: bulk ------------------------------------------------ Paper Submission Deadline: January 10, 1996 (Wednesday) ------------------------------------------------ CALL FOR PAPERS AND PARTICIPATION Genetic Programming 1996 Conference (GP-96) July 28 - 31 (Sunday - Wednesday), 1996 Fairchild Auditorium - Stanford University - Stanford, California Proceedings will be published by The MIT Press In cooperation with the Association for Computing Machinery (ACM), SIGART, the IEEE Neural Network Council, and the American Association for Artificial Intelligence. Genetic programming is a domain-independent method for evolving computer programs that solve, or approximately solve, problems. Starting with a primordial ooze of thousands of randomly created programs composed of functions and terminals appropriate to a problem, a genetic population is progressively evolved over many generations by applying the Darwinian principle of survival of the fittest, a sexual recombination operation, and occasional mutation. This first genetic programming conference will feature contributed papers, tutorials, invited speakers, and informal meetings. Topics include, but are not limited to, applications of genetic programming, theoretical foundations of genetic programming, implementation issues, parallelization techniques, technique extensions, implementations of memory and state, representation issues, new operators, architectural evolution, evolution of mental models, cellular encoding, evolution of machine language programs, evolvable hardware, combinations with other machine learning techniques, and relations to biology and cognitive systems. ------------------------------------------------- HONORARY CHAIR: John Holland, University of Michigan INVITED SPEAKERS: John Holland, University of GENERAL CHAIR: John Koza, Stanford University PUBLICITY CHAIR: Patrick Tufts, Brandeis University ------------------------------------------------- SPECIAL PROGRAM CHAIRS: The main focus of the conference (and about two-thirds of the papers) will be on genetic programming. In addition, papers describing recent developments in the following closely related areas of evolutionary computation (particularly those addressing issues common to various areas of evolutionary computation) will be reviewed by special program committees appointed and supervised by the following special program chairs. University of Illinois, Urbana, Illinois - CLASSIFIER SYSTEMS: Rick Riolo, University of Michigan - EVOLUTIONARY PROGRAMMING AND EVOLUTION Diego, California ------------------------------------------------- TUTORIALS -Sunday July 28 9:15 AM - 11:30 AM Illinois - Machine Language Genetic Programming - Peter Nordin, University of Dortmund, Germany - Genetic Programming using Mathematica P Robert Nachbar P Merck Research Laboratories - Introduction to Genetic Programming - John Koza, Stanford University ------------------------------------------------- Sunday July 28 1:00 PM - 3: 15 PM - Classifier Systems- Robert Elliott Smith, University of Alabama - Evolutionary Computation for Constraint Optimization - Zbigniew Michalewicz, University of North Carolina - Advanced Genetic Programming - John Koza, Stanford University ------------------------------------------------- Sunday July 28 3:45 PM - 6 PM - Evolutionary Programming and Evolution Strategies - - Cellular Encoding P Frederic Gruau, Stanford University person) - Genetic Programming with Linear Genomes (one hour) - Wolfgang Banzhaf, University of Dortmund, Germany -JECHO - Terry Jones, Santa Fe Institute ------------------------------------------------- Tuesday July 30 - 3 PM - 5:15PM University - Machine Learning - Pat Langley, Stanford University -JMolecular Biology for Computer Scientists - Russ B. Altman, Stanford University ------------------------------------------------- INFORMATION FOR SUBMITTING PAPERS The deadline for receipt at the physical mail address below of seven (7) copies of each submitted paper is Wednesday, January 10, 1996. Papers are to be in single-spaced, 12- point type on 8 1/2" x 11" or A4 paper (no e-mail or fax) with full 1" margins at top, bottom, left, and right. Papers are to contain ALL of the following 9 items, within a maximum of 10 pages, IN THIS ORDER: (1) title of paper, (2) author name(s), (3) author physical address(es), (4) author e-mail address(es), (5) author phone number(s), (6) a 100-200 word abstract of the paper, (7) the paper's category (chosen from one of the following five alternatives: genetic programming, genetic algorithms, classifier systems, evolutionary programming, or evolution strategies), (8) the text of the paper (including all figures and tables), and (9) bibliography. All other elements of the paper (e.g., acknowledgments, appendices, if any) must come within the maximum of 10 pages. Review criteria will include significance of the work, novelty, sufficiency of information to permit replication (if applicable), clarity, and writing quality. The first-named (or other designated) author will be notified of acceptance or rejection by approximately Monday February 26, 1996. The style of the camera-ready paper will be identical to that of the 1994 Simulation of Adaptive Behavior conference published by the MIT Press. Depending on the number, subject, and content of the submitted papers, the program committee may decide to allocate different number of pages to various accepted papers. The deadline for the camera-ready, revised version of accepted papers will be announced, but will be approximately Wednesday March 20, 1996. Proceedings will be published by The MIT Press and will be available at the conference (and, if requested, by priority mail to registered conference attendees with U.S. addresses just prior to the conference). One author will be expected to present each accepted paper at the conference. ------------------------------------------------- FOR MORE INFORMATION ABOUT THE GP-96 CONFERENCE: On the World Wide Web: http://www.cs.brandeis.edu/~zippy/gp-96.html or via e-mail at gp@aaai.org. Conference operated by Genetic Programming Conferences, Inc. (a California not-for-profit corporation). ------------------------------------------------- FOR MORE INFORMATION ABOUT GENETIC PROGRAMMING IN GENERAL: http://www-cs- faculty.stanford.edu/~koza/. ------------------------------------------------- FOR MORE INFORMATION ABOUT DISCOUNTED TRAVEL : For further information regarding special GP-96 airline and car rental rates, please contact Conventions in America at e-mail flycia@balboa.com; or phone 1-800-929-4242; or phone 619-678-3600; or FAX 619-678-3699. ------------------------------------------------- FOR MORE INFORMATION ABOUT THE SAN FRANCISCO BAY AREA AND SILICON VALLEY AREA SIGHTS: Try the Stanford University home page at http://www.stanford.edu/, the Hyperion Guide at http://www.hyperion.com/ba/sfbay.html; the Palo Alto weekly at http://www.service.com/PAW/home.html; the California Virtual Tourist at http://www.research.digital.com/SRC/virtual- tourist/California.html; and the Yahoo Guide of San Francisco at http://www.yahoo.com/Regional_Information/States/Califo rnia/San_Francisco. ------------------------------------------------- FOR MORE INFORMATION ABOUT CONTEMPORANEOUS WEST COAST CONFERENCES: Information about the AAAI-96 conference on August 4 P 8 (Sunday P Thursday), 1996, in Portland, Oregon can be found at http://www.aaai.org/. For information on the International Conference on Knowledge Discovery and Data Mining (KDD-96) in Portland, Oregon, on August 3- 5, 1996: http://www-aig.jpl.nasa.gov/kdd96. Information about the Foundations of Genetic Algorithms (FOGA) workshop on August 3 P 5 (Saturday P Monday), 1996, in San Diego, California can be found at http://www.aic.nrl.navy.mil/galist/foga/ or by contacting belew@cs.wisc.edu. ------------------------------------------------- FOR MORE INFORMATION ABOUT MEMBERSHIP IN THE ACM, AAAI, or IEEE: For information about ACM membership, try http://www.acm.org/; for information about SIGART, try http://sigart.acm.org/; for AAAI membership, go to http://www.aaai.org/; and for membership in the IEEE Computer Society, go to http://www.computer.org. ------------------------------------------------- PHYSICAL MAIL ADDRESS FOR GP-96: GP-96 Conference, c/o American Association for Artificial Intelligence, 445 Burgess Drive, Menlo Park, CA 94025. PHONE: 415-328-3123. FAX: 415-321-4457. WWW: http://www.aaai.org/. E-MAIL: gp@aaai.org. ------------------------------------------------ REGISTRATION FORM FOR GENETIC PROGRAMMING 1996 CONFERENCE TO BE HELD ON JULY 28 P 31, 1996 AT STANFORD UNIVERSITY First Name _________________________ Last Name_______________ Affiliation________________________________ Address__________________________________ ________________________________________ City__________________________ State/Province _________________ Zip/Postal Code____________________ Country__________________ Daytime telephone__________________________ E-Mail address_____________________________ Conference registration fee includes copy of proceedings, attendance at 4 tutorials of your choice, syllabus books for 4 tutorials, conference reception, and admission to conference. Students must send legible proof of full-time student status. Conference proceedings will be mailed to registered attendees with U.S. mailing addresses via 2-day U.S. priority mail 1 P 2 weeks prior to the conference at no extra charge (at addressee's risk). If you are uncertain as to whether you will be at that address at that time or DO NOT WANT YOUR PROCEEDINGS MAILED to you at the above address for any other reason, your copy of the proceedings will be held for you at the conference registration desk if you CHECK HERE ____. Postmarked by May 15, 1996: Student P ACM, IEEE, or AAAI Member $195 Regular P ACM, IEEE, or AAAI Member $395 Student P Non-member $215 Regular P Non-member $415 Postmarked by June 26, 1996: Student P ACM, IEEE, or AAAI Member $245 Regular P ACM, IEEE, or AAAI Member $445 Student P Non-member $265 Regular P Non-member $465 Postmarked later or on-site: Student P ACM, IEEE, or AAAI Member $295 Regular P ACM, IEEE, or AAAI Member $495 Student P Non-member $315 Regular P Non-member $515 Member number: ACM # ___________ IEEE # _________ AAAI # _________ Total fee (enter appropriate amount) $ _________ __ Check or money order made payable to "AAAI" (in U.S. funds) __ Mastercard __ Visa __ American Express Credit card number __________________________________________ Expiration Date ___________ Signature _________________________ TUTORIALS: Check off a box for one tutorial from each of the 4 columns: Sunday July 28, 1996 P 9:15 AM - 11:30 AM __ Genetic Algorithms __ Machine Language GP __ GP using Mathematica __ Introductory GP Sunday July 28, 1996 P 1:00 PM - 3: 15 PM __ Classifier Systems __ EC for Constraint Optimization __ Advanced GP Sunday July 28, 1996 P 3:45 PM - 6 PM __ Evolutionary Programming and Evolution Strategies __ Cellular Encoding __ GP with Linear Genomes __ ECHO Tuesday July 30, 1996 P3:00 PM - 5:15PM __ Neural Networks __ Machine Learning __ Molecular Biology for Computer Scientists __ Check here for information about housing and meal package at Stanford University. __ Check here for information on student travel grants. No refunds will be made; however, we will transfer your registration to a person you designate upon notification. SEND TO: GP-96 Conference, c/o American Association for Artificial Intelligence, 445 Burgess Drive, Menlo Park, CA 94025. PHONE: 415- 328-3123. FAX: 415-321-4457. E-MAIL: gp@aaai.org. WWW: http://www.aaai.org/. ------------------------------------------------- PROGRAM COMMITTEE Russell J. Abbott California State University, Los Angeles and The Aerospace Corporation Hojjat Adeli Ohio State University Dennis Allison Stanford University Lee Altenberg Hawaii Institute of Geophysics and Planetology Peter J. Angeline Loral Federal Systems Wolfgang Banzhaf University of Dortmund, Germany Rik Belew University of California at San Diego Samy Bengio Centre National d'Etudes des Telecommunications, France Forrest H. Bennett III Genetic Algorithms Technology Corporation Scott Brave Stanford University Bill P. Buckles Tulane University Walter Cedeno Primavera Systems Inc. Nichael Lynn Cramer BBN System and Technologies Jason Daida University of Michigan Patrik D'haeseleer University of New Mexico Marco Dorigo Universite' Libre de Bruxelles Bertrand Daniel Dunay System Dynamics International Andrew N. Edmonds Science in Finance Ltd., UK H.H. Ehrenburg CWI, The Netherlands Frank D. Francone FRISEC P Francone & Raymond Institute for the Study of Evolutionary Computation, Germany Adam P. Fraser University of Salford Alex Fukunaga University of California, Los Angeles Frederic Gruau Stanford University Richard J. Hampo Ford Motor Company Simon Handley Stanford University Thomas D. Haynes The University of Tulsa Hitoshi Hemmi ATR, Kyoto, Japan Vasant Honavar Iowa State University Thomas Huang University of Illinois Hitoshi Iba Electrotechnical Laboratory, Japan Christian Andrew Johnson Department of Economics, University of Santiago Martin A. Keane Econometrics Inc. Mike Keith Allen Bradley Controls Maarten Keijzer Kenneth E. Kinnear, Jr. Adaptive Computing Technology W. B. Langdon University College, London Kenneth Marko Ford Motor Company Martin C. Martin Carnegie Mellon University Sidney R Maxwell III Nicholas Freitag McPhee University of Minnesota, Morris Heinz Muehlenbein GMD Research Center, Germany Robert B. Nachbar Merck Research Laboratories Peter Nordin University of Dortmund, Germany Howard Oakley Institute of Naval Medicine, UK Franz Oppacher Carleton University, Ottawa Una-May O`Reilly Carleton University, Ottawa Michael Papka Argonne National Laboratory Timothy Perkis Frederick E. Petry Tulane University Bill Punch Michigan State University Justinian P. Rosca University of Rochester Conor Ryan University College Cork, Ireland Malcolm Shute University of Brighton, UK Eric V. Siegel Columbia University Karl Sims Andrew Singleton Creation Mechanics Lee Spector Hampshire College Walter Alden Tackett Neuromedia Astro Teller Carnegie Mellon University Marco Tomassini Ecole Polytechnique Federale de Lausanne Patrick Tufts Brandeis University V. Rao Vemuri University of Califonia at Davis Peter A. Whigham Australia Darrell Whitley Colorado State University Man Leung Wong Chinese University of Hong Kong Alden H. Wright University of Montana Byoung-Tak Zhang GMD, Germany From owner-gann-list Fri Nov 17 12:30:52 1995 Received: (from mdomo@localhost) by cs.iastate.edu (8.7.1/8.7.1) id MAA05184 for gann-list-outgoing; Fri, 17 Nov 1995 12:06:45 -0600 (CST) Received: from ren.cs.iastate.edu (ren.cs.iastate.edu [129.186.3.41]) by cs.iastate.edu (8.7.1/8.7.1) with ESMTP id MAA05178 for ; Fri, 17 Nov 1995 12:06:41 -0600 (CST) From: GANN List Admin Received: (from gannadm@localhost) by ren.cs.iastate.edu (8.7.1/8.7.1) id MAA18126 for gann-list@cs.iastate.edu; Fri, 17 Nov 1995 12:06:39 -0600 (CST) Reply-To: qin@autom.fpms.ac.be (Qin Liang) X-Originator: qin@autom.fpms.ac.be (Qin Liang) with TCP; Thu, 16 Nov 95 09:45:52 +0100 Date: Thu, 16 Nov 1995 09:52:38 GMT Message-Id: <199511160952.JAA26214@autom.fpms.ac.be> To: gann-list@cs.iastate.edu Subject: Neural Network Software Cc: qin@autom.fpms.ac.be X-Sun-Charset: US-ASCII Sender: owner-gann-list@cs.iastate.edu Precedence: bulk The first line of my mail was missing. That is why I would like to send it again. Sorry for disturbing you. Liang Qin Dear Colleagues, last few years. We are going to gather information on Neural Network software that have been used in different fields. If you are involved somehow in developing or using Neural Network software, we appreciate the information on existing software, such as name of the software, neural netwok models implemented, performance comparisons, advantages and disadvantages and ftp-site. Once the sufficient information is received, we will compile a survey for the list. Please send your information to following address. Thanks. Sincerely yours, ======================================================================== _/ LIANG Qin _/ _/ Laboratoire d'Automatique _/ Faculte Polytechnique de Mons _/ Boulevard Dolez, 31 _/ _/ B-7000 Mons _/_/_/_/ Belgium E-Mail: qin@autom.fpms.ac.be ========================================================================