Genetic Algorithms Digest Thursday, May 13, 1999 Volume 13 : Issue 8 - Do NOT send email or reply to gadistr@aic.nrl.navy.mil - Send submissions (articles) to GA-List@aic.nrl.navy.mil - Send administrative requests (subscribe, unsubscribe, change of address, etc.,) to GA-List-Request@aic.nrl.navy.mil ********************************************************************** You can access back issues, GA code, conference announcements, etc., either through the WWW at URL http://www.aic.nrl.navy.mil/galist/ or through anonymous ftp at ftp.aic.nrl.navy.mil [132.250.84.25] in /pub/galist. ********************************************************************** Today's Topics: - Re: Implementation of Evolutionary Strategies (Correction) (v13n7) - Re: Niching and Co-Evolution combined (Re: v13n7) - GA for CDO problem - job vacancies - Opportunity: Scientist/Prod Dev Eng. - (Req.'s: GA/EE/NP Comp) - neuro-evolution software, papers, web demos available - Announcement: extended deadline for the EA'99 conference. - APGA'2000: Call for papers - CALL FOR LATE-BREAKING PAPERS --- GECCO-99 - Late Breaking Papers at EuroGP'99 - Nostradamus Prediction Conference - CALL FOR PAPERS NIPS*99 - PATAT 2000 Call for Papers ---------------------------------------------------------------------- CALENDAR OF GA-RELATED ACTIVITIES: (with GA-List issue reference) EuroGP99 2nd Euro Workshop on GP, Goteborg, Sweden May 26-29, 99 (v12n20) EvoIASP99 1st Euro WS on EC in Image Anal & Sig Proc May 28, 99 (v12n18) EuroEctel99 1st Euro Workshop on EC in Telecommun May 29, 99 (v12n16) EUROGEN99 Short Course on EAs, Jyvaskyla, Finland May 30-Jun3, 99 (v13n3) SOCO99 Soft Computing, Genova, Italy Jun 1-4, 99 (v12n8) 1999 Complex Systems Summer School Jun 6-Jul 2, 99 (v13n2) ISAMA99 Int Soc for Arts, Math and Arch, Spain Jun 7-11, 99 (v12n21) MENDEL99 5th Int Mendel Conf on Soft Comp, Czech Rep Jun 9-12, 99 (v12n23) TAINN99 8th Turkish Symposium on AI and Neural Nets Jun 23-25, 99 (v12n17) CEF99 EC in Economics and Finance, Chestnut Hill, MA Jun 24-26, 99 (v12n21) ICML99 16th Int Conf on Mach Learning, Bled, Slovenia Jun 27-30, 99 (v12n21) Recent Advances in Soft Computing99, Leicester, UK Jul 1-2, 99 (v12n20) CEC99 Congress on Evol Computation, Washington, DC Jul 6-9, 99 (v12n9) ACAI99 Workshop on ML and Int Agents, Chania, Greece Jul 5-16, 99 (v13n3) Nostradamus Prediction Conference, Zlin, Czech Rep Jul 10 - Aug 10,99 (v13n8) GECCO99 Genetic & Evol Computation Conf, Orlando, FL Jul 13-17, 99 (v12n8) AAAI99 16th National Conference on AI, Orlando, FL Jul 18-22, 99 (v12n21) EH99 1st NASA/DOD WS on Evol Hardware, Pasadena, CA Jul 19-21, 99 (v12n23) IJCAI99 WS on Neur, Symb, & Reinfcmt Meth for Sequ Lear Aug 1, 99 (v13n1) IJCAI99 WS on Agents Learning About, From, and With Ot Aug 2, 99 (v12n22) IPCAT99 3rd Int WS on Info Proc in Cells and Tissues Aug 23-26, 99 (v13n3) KES99 3rd Int Conf on KB Intel Inf Eng Sys, Australia Aug 31-Sep 1 99 (v13n7) ECAL99 5th Euro Conf on Artificial Life, Lausanne, Swi Sep 13-17, 99 (v12n20) EUFIT99 7th Euro Conf on Intell Tech and Soft Comp Sep 13-16, 99 (v13n3) SMC99 Int Conf on System, Man, and Cybernetics, Tokyo Oct 12-15, 99 (v13n4) EA99 Artificial Evolution, Dunkerque, France Nov 3-5, 99 (v13n5) ANNIE99 Artificial NN in Engineering, St. Louis, MO Nov 7-10, 99 (v13n5) RSFDGrC99 7th Int WS Rough Sets, Fuzzy Sets, Data Min Nov 9-11, 99 (v12n22) NIPS99 Neural Information Processing Systems, Denver, CO Dec 4, 99 (v13n8) IAT99 Intelligent Agent Technology, Hong Kong Dec 15-17, 99 (v12n21) APGA2000 2nd Asia Pac Conf on GAs and Applications, HK May 3-5, 00 (v13n8) WAC2000 8th Int Sym on Robotics with Apps, Maui, Hawaii Jun 11-16, 00 (v13n7) PATAT2000 3rd Int Conf Prac & Theor of Auto Timetabling Aug 16-18, 00 (v13n8) Send announcements of other activities to GA-List@aic.nrl.navy.mil. ------------------------------ Date: Tue, 20 Apr 1999 10:07:50 +0100 From: Joao Carlos Costa Subject: Re: Implementation of Evolutionary Strategies (Correction) (v13n7) Hi, I am very sorry, but my previous message had a small but significant mistake: Our results were **not** as good as the ones in the book. (That is why we are trying to look at other implementations :-) Once again, my apologies, Thanks in advance, Joao Costa > Does anyone know where can I find a reference implementation of > Evolutionary Strategies? I and a couple of coleagues have implemented > ES, and have been trying to replicate the results of Prof. Back's book > "Evolutionary Algorithms in Theory and Practice" as a test to the > library. Since our results are as good as the ones in the book, we > would like to look at other implementations, in order to find out what > our error might be. ------------------------------ Date: Tue, 11 May 1999 21:17:01 +0100 From: Vesselin Vassilev Subject: Re: Niching and Co-Evolution combined (Re: v13n7) Dear Ariel I do not know whether I have done enough work in this direction to recommend, however, I feel that one of my latest papers could be useful for you. V. K. Vassilev, J. F. Miller, T. C. Fogarty (1999). "Co-evolving demes of non-uniform cellular automata for synchronisation", in A. Stoica, D. Keymeulen, and J. Lohn (eds.) Proceedings of the 1st NASA/DoD Workshop on Evolvable Hardware (July 19-21, Pasadena, CA), IEEE Computer Society Press. The paper is available via http://www.dcs.napier.ac.uk/~vesselin/papers/eh99-1.ps.gz Sincerely yours Vesco Ph.D. student Napier University ------------------------------ Date: Thu, 22 Apr 1999 03:06:13 +0700 From: "Firman Bachter" Subject: GA for CDO problem Dear Sir, Can you send me the application of GA for CDO (Cost Drivers Optimizing) in Activity Based Costing? (source code is written in Pascal or C/C++ or anything else). I want to use the application for my thesis at university. Thank you very much for your help. Sincerely Firman Bachter ------------------------------ Date: Wed, 21 Apr 1999 16:41:01 +0100 (BST) From: Xin Yao Subject: job vacancies Dear colleagues, This is just a gentle reminder that the deadline for applying for the following two posts is 22 April 1999 (though late applications may be considered): (1) Lectureship in Computer Science (preferably evolutionary computation) (2) Research Fellow in Evolutionary Computation More information about application (including electronic application) and further particulars can be found from the following address: URL: http://www.cs.bham.ac.uk/school/jobvacancies.html Best regards, Xin Yao ------------------------------ Date: Tue, 20 Apr 1999 07:56:38 -0700 From: "Lee Marc" Subject: Opportunity: Scientist/Prod Dev Eng. - (Req.'s: GA/EE/NP Comp) Greetings! My name is Lee Marc. I'm the Managing Director of Morgan Kennedy Inc., a High-Technology Venture Capital Organization here in the Silicon Valley. We're looking for Research Scientist/Product Development Engineer for a San Jose CA based software company. This person will apply their knowledge in Genetic Algorithms and Fuzzy Logic to solve real-life NP Complete problems in the area of Digital Logic Design and Verification. Additional exposure to or experience with ASIC engineering or Chip Design, Electronic Design Automation (EDA), and programming with Verilog, VHDL, C, C++, and Java are a definite plus. Academic coursework in Electrical Engineering and/or Mathematics is helpful and a Masters level Education and/or Ph.D. is preferred. Our client company creates an EDA toolset for chip designers and developers. The toolset embodies a system validation environment capable of automatic functional test generation. Using our clients software, chip developers and designers speed up and enhance the development, verification and validation of highly integrated devices. This toolset enables companies both large and small to enjoy fast cycle, first pass, functional silicon success - while avoiding costly ASIC turns and minimizing difficult prototype debugging. [Moderators' note: This posting has been shortened. For more information contact the person below. ] Lee A. Marc Morgan Kennedy, Inc. (650) 566-9800 mailto:lmarc@morgankennedy.com ------------------------------ Date: Sun, 25 Apr 1999 22:06:32 -0500 From: risto@cs.utexas.edu Subject: neuro-evolution software, papers, web demos available The JavaSANE software package for evolving neural networks with genetic algorithms is available from the UTCS Neural Networks Research Group website, http://www.cs.utexas.edu/users/nn. The SANE method has been designed as part of our ongoing research in efficient neuro-evolution. This software is intended to facilitate applying neuro-evolution to new domains and problems, and also as a starting point for future research in neuro-evolution algorithms. Abstracts of recent papers on eugenic evolution, on-line evolution, and non-Markovian control are also included below. Demos of these systems as well as other neuroevolution papers are available at http://www.cs.utexas.edu/users/nn/pages/research/neuroevolution.html. -- Risto Software: ========= JAVASANE: SYMBIOTIC NEURO-EVOLUTION IN SEQUENTIAL DECISION TASKS http://www.cs.utexas.edu/users/nn/pages/software/abstracts.html#javasane Cyndy Matuszek, David Moriarty The JavaSANE package contains the source code for the Hierarchical SANE neuro-evolution method, where a population of neurons is evolved together with network blueprints to find a network for a given task. The method has been shown effective in several sequential decision tasks including robot control, game playing, and resource optimization. JavaSANE is designed especially to make it possible to apply SANE to new tasks with minimal effort. It is also intended to be a platform-independent and parsimonious implementation of SANE, so that can serve as a starting point for further research in neuro-evolution algorithms. (This package is written in Java; an earlier C-version is also available). Papers and Demos: ================= SOLVING NON-MARKOVIAN CONTROL TASKS WITH NEUROEVOLUTION Faustino Gomez and Risto Miikkulainen To appear in Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI-99, Stockholm, Sweden) (6 pages). http://www.cs.utexas.edu/users/nn/pages/publications/ abstracts.html#gomez.ijcai9.ps.gz The success of evolutionary methods on standard control learning tasks has created a need for new benchmarks. The classic pole balancing problem is no longer difficult enough to serve as a viable yardstick for measuring the learning efficiency of these systems. The double pole case, where two poles connected to the cart must be balanced simultaneously is much more difficult, especially when velocity information is not available. In this article, we demonstrate a neuroevolution system, Enforced Sub-populations (ESP), that is used to evolve a controller for the standard double pole task and a much harder, non-Markovian version. In both cases, our results show that ESP is faster than other neuroevolution methods. In addition, we introduce an incremental method that evolves on a sequence of tasks, and utilizes a local search technique (Delta-Coding) to sustain diversity. This method enables the system to solve even more difficult versions of the task where direct evolution cannot. A demo of ESP in the 2-pole balancing task can be seen at http://www.cs.utexas.edu/users/nn/pages/research/neuroevolution.html. REAL-TIME INTERACTIVE NEURO-EVOLUTION Adrian Agogino, Kenneth Stanley, and Risto Miikkulainen Technical Report AI98-266, Department of Computer Sciences, The University of Texas at Austin, 1998 (16 pages). http://www.cs.utexas.edu/users/nn/pages/publications/ abstracts.html#agostan.ineps.Z In standard neuro-evolution, a population of networks is evolved in the task, and the network that best solves the task is found. This network is then fixed and used to solve future instances of the problem. Networks evolved in this way do not handle real-time interaction very well. It is hard to evolve a solution ahead of time that can cope effectively with all the possible environments that might arise in the future and with all the possible ways someone may interact with it. This paper proposes evolving feedforward neural networks online to create agents that improve their performance through real-time interaction. This approach is demonstrated in a game world where neural-network-controlled individuals play against humans. Through evolution, these individuals learn to react to varying opponents while appropriately taking into account conflicting goals. After initial evaluation offline, the population is allowed to evolve online, and its performance improves considerably. The population not only adapts to novel situations brought about by changing strategies in the opponent and the game layout, but it also improves its performance in situations that it has already seen in offline training. This paper will describe an implementation of online evolution and shows that it is a practical method that exceeds the performance of offline evolution alone. A demo of on-line evolution in the real-time gaming task is at http://www.cs.utexas.edu/users/nn/pages/research/neuroevolution.html. EUGENIC EVOLUTION FOR COMBINATORIAL OPTIMIZATION John W. Prior Master's Thesis, Technical Report AI98-268, Department of Computer Sciences, The University of Texas at Austin, 1998 (126 pages). http://www.cs.utexas.edu/users/nn/pages/publications/ abstracts.html#prior.eugenc-thesis.ps.Z In the past several years, evolutionary algorithms such as simulated annealing and the genetic algorithm have received increasing recognition for their ability to optimize arbitrary functions. These algorithms rely on the process of Darwinian evolution, which promotes highly successful solutions that result from random variation. This variation is produced by the random operators of mutation and/or recombination. These operators make no attempt to determine which alleles or combinations of alleles are most likely to yield overall fitness improvement. This thesis will explore the benefits that can be gained by utilizing a direct analysis of the correlations between fitness and alleles or allele combinations to intelligently and purposefully design new highly-fit solutions. An algorithm is developed in this thesis that explicitly analyzes allele-fitness distributions and then uses the information gained from this analysis to purposefully construct new individuals ``bit by bit''. Explicit measurements of ``gene significance'' (the effect of a particular gene upon fitness) allows the algorithm to adaptively decide when conditional allele-fitness distributions are necessary in order to correctly track important allele interactions. A new operator---the ``restriction'' operator---allows the algorithm to simply and quickly compute allele selection probabilities using these conditional fitness distributions. The resulting feedback from the evaluation of new individuals is used to update the statistics and therefore guide the creation of increasingly better individuals. Since explicit analysis and creation is used to guide this evolutionary process, it is not a form of Darwinian evolution. It is a pro-active, contrived process that attempts to intelligently create better individuals through the use of a detailed analysis of historical data. It is therefore a eugenic evolutionary process, and thus this algorithm is called the ``Eugenic Algorithm'' (EuA). The EuA was tested on a number of benchmark problems (some of which are NP-complete) and compared to widely recognized evolutionary optimization techniques such as simulated annealing and genetic algorithms. The results of these tests are very promising, as the EuA optimized all the problems at a very high level of performance, and did so much more consistently than the other algorithms. In addition, the operation of EuA was very helpful in illustrating the structure of the test problems. The development of the EuA is a very significant step to statistically justified combinatorial optimization, paving the way to the creation of optimization algorithms that make more intelligent use of the information that is available to them. This new evolutionary paradigm, eugenic evolution will lead to faster and more accurate combinatorial optimization and to a greater understanding of the structure of combinatorial optimization problems. FAST REINFORCEMENT LEARNING THROUGH EUGENIC NEURO-EVOLUTION Daniel Polani and Risto Miikkulainen Technical Report AI99-277, Department of Computer Sciences, University of Texas at Austin, 1999 (7 pages). http://www.cs.utexas.edu/users/nn/pages/publications/ abstracts.html#polani.eusae-99.ps.gz In this paper we introduce EuSANE, a novel reinforcement learning algorithm based on the SANE neuro-evolution method. It uses a global search algorithm, the Eugenic Algorithm, to optimize the selection of neurons to the hidden layer of SANE networks. The performance of EuSANE is evaluated in the two-pole balancing benchmark task, showing that EuSANE is significantly stronger than other reinforcement learning methods to date in this task. ------------------------------ Date: Tue, 11 May 1999 11:07:02 +0200 From: Denis Robilliard Subject: Announcement: extended deadline for the EA'99 conference. Please, take note of the new deadline for the EA'99 Conference on Artificial Evolution, to be held in Dunkerque (Dunkirk), France. The new deadline for reception of papers is: May, the 25th 1999. More informations are available at: http://www-lil.univ-littoral.fr/EA99/ -- Denis Robilliard ( http://www-lil.univ-littoral.fr/~robillia ) Laboratoire d'Informatique du Littoral BP 719 tel: 03.21.97.00.46 62228 Calais Cedex fax: 03.21.19.06.61 ------------------------------ Date: Tue, 27 Apr 1999 17:20:53 +0800 From: "Xie Jinxing" Subject: APGA'2000: Call for papers APGA'2000 The Second Asia-Pacific Conference on Genetic Algorithms and Applications May 3-5, 2000, Hong Kong http://orsc.edu.cn/apga2000 Conference Objectives In order to promote international academic exchanges on genetic algorithms, it is decided that the Second Asia-Pacific Conference on Genetic Algorithms and Applications (APGA'2000) will be held at the City University of Hong Kong from 3-5 May, 2000. The previous Conference (APGA'98) was held at Tsinghua University, Beijing, China from 18-20 October, 1998. The Conference will be devoted to the discussion of genetic algorithms, simulated annealing and artificial neural networks as well as their applications in - Optimization and Control - Information Systems - Bio-informatics - Engineering Design - Emergent Systems - Pattern Recognition - Production Planning and Scheduling - Financial Engineering - Manufacturing Systems - Probability Models - Machine Learning - Fuzzy Systems - System Reliability - Business and Management Contributed Papers Scholars are invited to send their contributions. Papers will be selected based on their originality, timeliness, significance, relevance, and clarity of presentation. Camera-ready manuscripts of papers are required after the Conference Committee accepts their papers. They should be submitted to one of the Conference Chairmen by February 15, 2000. Submission Instructions Prospective speakers should submit their papers to one of the Conference Chairmen by November 1, 1999 by post/e-mail. Each paper must also contain all the following: (1) paper title, (2) abstract, (3) author(s) name(s), organization name, and full mailing address, with the indication of the presenter, and (4) e-mail address if available. Registration Fee The registration fee is US$300, including page charge and admission to all sessions, reception party, banquet and coffee breaks. One of the authors is required to pre-register for the Conference by February 15, 2000. An additional of US$100 for each paper is required for multiple paper submissions. No requests for refunds will be accepted if made after April 1, 2000. Further Information For information updates, please visit the Conference webpage at http://orsc.edu.cn/apga2000. Conference Chairmen Prof. Kin Keung Lai Faculty of Business City University of Hong Kong Tat Chee Avenue, Kowloon, HK Tel: (852) 2788-8563 E-mail: mskklai@cityu.edu.hk Prof. Osamu Katai Department of Systems Science Graduate School of Informatics Kyoto University, Japan Tel: (81) 75-753-5201 E-mail: katai@prec.kyoto-u.ac.jp Important Dates - Full paper submission due: November 1, 1999 - Acceptance notification: December 15, 1999 - Submission of camera-ready manuscripts: February 15, 2000 [Moderator: For additional details please see conference homepage at http://orsc.edu.cn/apga2000.] ------------------------------ Date: Tue, 4 May 1999 16:32:55 -0500 (CDT) From: Erick Cantu-Paz Subject: CALL FOR LATE-BREAKING PAPERS --- GECCO-99 CALL FOR LATE-BREAKING PAPERS for the 1999 Genetic and Evolutionary Computation Conference GECCO-99 July 13 - 17 (Tuesday - Saturday), 1999 Omni Rosen Hotel, Orlando, Florida USA http://www-illligal.ge.uiuc.edu/gecco/ Deadline: Thursday, June 10, 1999 The Genetic and Evolutionary Computation Conference (GECCO-99) is seeking papers describing late-breaking developments in the field of genetic and evolutionary computation for inclusion in a special paperbound book to be distributed to all attendees of the GECCO-99 conference to be held on July 13 - 17 (Tuesday - Saturday), 1999 at the Omni Rosen Hotel, Orlando, Florida. This special book is distinct from the conference proceedings. The purpose of late-breaking papers is to provide conference attendees with information about research that was initiated, enhanced, improved, or completed after the original paper submission deadline in January 1999. Late-breaking papers will be presented during a poster session held during the GECCO-99 conference. The poster session is tentatively scheduled for Thursday evening, July 15, 199. Late-breaking papers will be briefly examined for relevance and minimum standards of acceptability, but will not be peer reviewed in detail. Authors will individually retain copyright (and all other rights) to their late-breaking papers and should feel free to submit them (either before or after the above deadline) for publication by other conferences or journals. Late-breaking papers must be submitted in camera-ready form in accordance with the final camera-ready GECCO-99 format specifications that can be found at the GECCO-99 WWW site at http://www-illigal.ge.uiuc.edu/gecco/ Late-breaking papers should be no more than 9 pages in length. Please send TWO camera-ready copies (printed with very high quality by laser printer) and the SIGNED "permission to publish" form (http://www-illigal.ge.uiuc.edu/gecco/cflbp.html) to GECCO-99 Late-Breaking Papers American Association for Artificial Intelligence 445 Burgess Drive Menlo Park, CA 94025.USA PHONE: 415-328-3123 E-MAIL: gecco@aaai.org No FAX or E-mail submissions can be accepted. ------------------------------ Date: Wed, 12 May 1999 13:03:35 +0200 From: Bill Langdon Subject: Late Breaking Papers at EuroGP'99 Details of the late breaking papers accepted at the Second European Workshop on Genetic Programming may be found at: http://www.cs.bham.ac.uk/~rmp/eebic/eurogp99/eurogp99_lbp.html Reminder: the workshop will be held 26-27 May. Information on registration, student travel funds and the other evolutionary computing workshops may be found at: http://www.dcs.napier.ac.uk/evonet/Coordinator/ News_and_events/evoworkshops99.html Thank you Bill W. B. Langdon, Phone +31 20 592 4093 Centrum voor Wiskunde en Informatica, Fax +31 20 592 4199 Kruislaan 413, NL-1098 SJ Amsterdam http://www.cwi.nl/~bill/ ------------------------------ Date: Tue, 20 Apr 1999 14:12:15 +0100 From: "Zelinka Ivan, Ing." Subject: Nostradamus Prediction Conference [Moderators' note: The following is an announcement for the Nostradamus Prediction Conference at the Technical University of Brno. ] Hello! [...] information about conference which is focused on prediction and behavior of dynamical systems (chaos, catastrophe,...). This conference will be held in South Moravian City Zlin from 7.10.1999 to 8.10.1999 at the Faculty of Technology, which is member of Technical University of Brno. It is organized by Department of Automatic Control. More information you can find on http://ft3.zlin.vutbr.cz/zelinka/nostra/nostra.htm Ivan Zelinka E-mail Zelinka@zlin.vutbr.cz http://ft3.zlin.vutbr.cz/Zelinka/home.htm Department of Automatic Control Faculty of Technology Technical University Zlin, Czech Republic Tel. ++420 67 / 721 15 21 Work ------------------------------ Date: Fri, 7 May 1999 17:15:59 -0400 (EDT) From: Lee Giles Subject: CALL FOR PAPERS NIPS*99 CALL FOR PAPERS -- NIPS*99 Neural Information Processing Systems -- Natural and Synthetic Monday November 29 - Saturday December 4, 1999 Denver, Colorado http://www.cs.cmu.edu/Web/Groups/NIPS This is the thirteenth meeting of an interdisciplinary conference which brings together cognitive scientists, computer scientists, engineers, neuroscientists, physicists, and mathematicians interested in all aspects of neural processing and computation. The conference will include invited talks as well as oral and poster presentations of refereed papers. The conference is single track and is highly selective. Preceding the main session, there will be one day of tutorial presentations (November 29), and following it there will be two days of focused workshops on topical issues at a nearby ski area (December 3-4). Major categories for paper submission, with example subcategories (by no means exhaustive), are as follows: Algorithms and Architectures: supervised and unsupervised learning algorithms, model selection algorithms, active learning algorithms, feedforward and recurrent network architectures, localized basis functions, mixture models, belief networks, graphical models, Gaussian processes, factor analysis, topographic maps, combinatorial optimization, hybrid symbolic-subsymbolic systems. Applications: handwriting recognition, sequence analysis, expert systems, fault diagnosis, medical diagnosis, analysis of medical images, data analysis, database mining, information retrieval, network traffic, music processing, time-series prediction, financial analysis. Cognitive Science/Artificial Intelligence: perception and psychophysics, neuropsychology, cognitive neuroscience, development, conditioning, human learning and memory, attention, language, natural language, reasoning, spatial cognition, emotional cognition, conceptual representation, neurophilosophy, problem solving and planning. Implementations: analog and digital VLSI, optical neurocomputing systems, novel neurodevices, computational sensors and actuators, simulation tools. Neuroscience: neural encoding, spiking neurons, synchronicity, sensory processing, systems neurophysiology, neuronal development, synaptic plasticity, neuromodulation, dendritic computation, channel dynamics, experimental data relevant to computational issues. Reinforcement Learning and Control: exploration, planning, navigation, Q-learning, TD-learning, state estimation, dynamic programming, robotic motor control, process control, Markov decision processes. Speech and Signal Processing: speech recognition, speech coding, speech synthesis, auditory scene analysis, source separation, applications of hidden Markov models to signal processing, models of human speech perception, auditory modeling and psychoacoustics. Theory: computational learning theory, statistical physics of learning, information theory, prediction and generalization, regularization, Boltzmann machines, Helmholtz machines, decision trees, support vector machines, online learning, dynamics of learning algorithms, approximation and estimation theory, learning of dynamical systems, complexity theory. Visual Processing: image processing, image coding, object recognition, visual psychophysics, stereopsis, motion detection and tracking. SUBMISSION DEADLINE: ELECTRONIC SUBMISSIONS MUST BE LOGGED BY MAY 21, 1999, AND HARD COPIES MUST BE RECEIVED BY THE SAME DATE. Hard copy submissions mailed from within the USA via first class mail will be accepted if postmarked on or before May 18, 1999. For general inquiries or requests for registration material E-mail: nipsinfo@salk.edu or Fax: (619) 587-0417 [Moderators' note: For more information see the conference Web site at http://www.cs.cmu.edu/Web/Groups/NIPS ] ------------------------------ Date: Mon, 10 May 99 10:01:46 BST From: Edmund Burke Subject: PATAT 2000 Call for Papers CALL FOR PAPERS PATAT 2000 The 3rd international conference on the Practice And Theory of Automated Timetabling Wednesday, 16th August - Friday, 18th August 2000 Fachhochschule Konstanz University of Applied Sciences Constance, Germany This conference is the third in a series of conferences that serve as a forum for an international community of researchers, practitioners and vendors on all aspects of computer-aided timetable generation. For more information about the series of conferences see http://www.asap.cs.nott.ac.uk/ASAP/ttg/patat-index.html The themes of the conference include (but are not limited to): o Sports Timetabling o Educational Timetabling o Transport Timetabling o Employee Timetabling o Complexity issues o Distributed timetabling systems o Experiences o Implementations o Commercial packages o Interactive vs batch timetabling o Timetable Updating o Relationship with other scheduling problems o Timetabling Research Areas, including: Constraint Based Methods Evolutionary Computation Artificial Intelligence Graph Colouring Expert Systems Heuristic Search Knowledge Based Systems Operational Research Simulated Annealing Local Search Mathematical Programming Soft Computing Tabu Search Deadlines: Paper/abstract submissions January 21st 2000 Notification of acceptance April 21st 2000 (at the latest) For more information, contact: Dr E.K.Burke Automated Scheduling and Planning Research Group. School of Computer Science and Information Technology University of Nottingham University Park, Nottingham NG7 2RD United Kingdom e-mail: ekb@cs.nott.ac.uk or Dr W.Erben Department of Computer Science FH Konstanz - University of Applied Sciences e-mail: erben@fh-konstanz.de PATAT 2000 WEB SITE Full updated information is always available from http://www.fh-konstanz.de/patat2000/ [Moderators' note: For more information see the conference Web site at http://www.fh-konstanz.de/patat2000/] ------------------------------ End of Genetic Algorithms Digest ******************************