Genetic Algorithms Digest Tuesday, November 28, 2000 Volume 14 : Issue 18 - 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 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: - Complex Systems Summer Schools, 2001 - 4 new Papers - CFP: IETE - CFP: ROPNET-2001 Workshop at GECCO-2001 - Soft Computing and Intelligent Systems - Quote from review - IlliGAL New Technical Reports Announcement (November, 2000) - Agents 2001 Call for Tutorials, Workshops and Demos - CEC 2001 CFP - Revised Deadline - IA and optimization - Welcome to the First ICSC Congress on Neuro-Fuzzy NF'2002 - CEC 2001 Competitions - CEC 2001 - Special Session on Surface and Curve Modelling - New Tech Report on Automatic Synthesis of Metabolic Pathways using GP ------------------------------------------------------------------------------- CALENDAR OF GA-RELATED ACTIVITIES: (with GA-List issue reference) ICARCV2000 6th Int Conf on Cont/Aut/Rob/Vis, Singapore Dec 6-8, 00 (v13n28) ISA2000 Int Congress on Intell Sys and Appl, Sydney, AU Dec 12-15, 00 (v14n5) KBCS2000 Int Conf on Knowl Based Comp Sys, Mumbai, India Dec 17-19, 00 (v14n9) Brain Machine Workshop, Ankara, Turkey Dec 20-22, 00 (v14n16) NNA2001 Neural Networks & Applications, Canary Is, Spain Feb 11-15, 01 (v14n16) FSFS2001 Fuzzy Sets & Fuzzy Systems, Canary Is, Spain Feb 11-15, 01 (v14n16) EC2001 Evolutionary Computation, Canary Is, Spain Feb 11-15, 01 (v14n16) EMO01 1st Int Con of Evol Multi-Criterion Opt, Zurich Mar 7-9, 01 (v14n4) SAC2001 16th ACM Symp on Applied Computing, Las Vegas Mar 11-14, 01 (v14n14) IWES01 3rd Int WS on Emergent Synthesis, Bled, Slovenia Mar 12-13, 01 (v14n15) CSMR2001 5th Eur Conf on Soft Maint and Reeng, Portugal Mar 14-16, 01 (v14n13) ISAS2001 Int Symp on Adaptive Systems, Havana, Cuba Mar 19-23, 01 (v14n16) ISI2001 Int Congress on Info Science Innovations, Dubai Mar 20-23, 01 (v13n25) PAKDD01 Pacific-Asia Conf on KD and Data Min, Hong Kong Apr 16-18, 01 (v14n15) EUROGP2001 4th Euro Conf on GP, Milan, Italy Apr 18-20, 01 (v14n15) EvoWorkshops2001 at the Euro Conf on GP, Milan, Italy Apr 18, 01 (v14n16) ICANNGA2001 5th Int Conf on Artif NN and GAs, Prague Apr 22-25, 01 (v14n11) CEC2001 Congress on EC, Seoul, Korea May 27-30, 01 (v14n15) Agents2001 5th Int Conf Autonomous Agents, Montreal May 28-Jun 1, 01 (v14n14) IC-AI2001 Int Conf on AI, Las Vegas, NV Jun 25-28, 01 (v14n16) SOCO Soft Computing & Intell Sys for Industry, Scotland Jun 26-29, 01 (v14n18) ICML2001 18th Int Conf on Machine Learning, MA Jun 28-Jul 1, 01 (v14n16) AIME01 8th Euro Conf on AI in Medicine, Portugal Jul 1-4, 01 (v14n16) GECCO2001 Gen & Evolutionary Computation Conf, SF, CA Jul 7-11, 01 (v14n16) TARK VIII 8th Conf Theor Aspects of Ratnlty & Knowl, It Jul 8-10, 01 (v14n16) WSC5 5th Online World Conf on Soft Computing Sep 4-18, 01 (v14n14) FUZZY DAYS Int Conf on Comp Intell, Dortmund, Germany Oct 1-3, 01 (v14n17) IAT2001 2nd Asia Pac Conf on Intell Agent Tech, Japan Oct 23-26, 01 (v14n14) ICDM01 IEEE Int Conf on Data Mining, Silicon Valley, Nov 29-Dec 2, 01 (v14n14) NF2002 1st Int ICSC Congress on Neuro-Fuzzy, Cuba Jan 15-18, 02 (v14n18) Send announcements of other activities to GA-List@aic.nrl.navy.mil. ------------------------------ Date: Wed, 15 Nov 2000 14:47:37 -0700 (MST) From: Melanie Mitchell Subject: Complex Systems Summer Schools, 2001 SANTA FE INSTITUTE Complex Systems Summer Schools Summer, 2001 SANTA FE SCHOOL: June 10 to July 7, 2001 in Santa Fe, New Mexico. Held on the campus of St. John's College in Santa Fe. Administered by the Santa Fe Institute. BUDAPEST SCHOOL: July 16 to August 10, 2001 in Budapest, Hungary. Held on the campus of Central European University in Budapest. Administered by Central European University and the Santa Fe Institute. GENERAL DESCRIPTION: An intensive introduction to complex behavior in mathematical, physical, living, and social systems for graduate students and postdoctoral fellows in the sciences and social sciences. Open to students in all countries. Students are expected to choose one school and attend the full four weeks. Week 1 will consist of an intensive series of lectures and laboratories introducing foundational ideas and tools of complex systems research. The topics will include nonlinear dynamics and pattern formation, statistical mechanics and stochastic processes, information theory and computation theory, adaptive computation, computer modeling tools, and specific applications of these core topics to various disciplines. Weeks 2 and 3 will consist of lectures and panel discussions on current research in complex systems. The topics this year are: -- Origin and Early Evolution of Life (Santa Fe and Budapest) -- Nonstandard Approaches to Computation (Santa Fe and Budapest) -- Geophysics and Climate Modeling (Santa Fe) -- Self-Organization and Collective Behavior (Budapest) Week 4 will be devoted to completion and presentation of student projects. WHO SHOULD APPLY: Applications are solicited from graduate students and postdoctoral fellows in any discipline, but with some background in science and mathematics at least at the undergraduate level (including calculus and linear algebra). An optional review of relevant mathematics will be given at the beginning of each school. Students may apply to either the Santa Fe School or the Budapest School, regardless of home country. COSTS: -- Santa Fe School: No tuition is charged. 100% of housing costs are provided for graduate students and 50% for postdoctoral fellows. (The remaining 50% is $700 for the four week school). Most students will provide their own travel funding. Some travel scholarships may be available, depending on need. -- Budapest School: No tuition is charged. 100% of housing costs are provided for all students. Some travel scholarships will be available, depending on need. HOUSING: Housing at both schools will be in single dormitory rooms, some with shared bathrooms. Telephone and computer network connectors will be available. For students with accompanying families, some family housing will be available. Travel support for families is not available. APPLICATION INSTRUCTIONS: Provide a current resume with publications list (if any), statement of current research interests, comments about why you want to attend the school, and two letters of recommendation from scientists who know your work. Include your e-mail address and fax number. Specify which school you want to attend (or which is your first choice if you are willing to attend either). Specify in your cover letter whether you wish to apply for a travel scholarship. (This will not affect our decision on your application.) Send only complete application packages by postal mail to: Summer Schools Santa Fe Institute 1399 Hyde Park Road Santa Fe, NM 87501 APPLICATION DEADLINE: February 5,2001 Women, minorities, and students from developing countries are especially encouraged to apply. Further information at http://www.santafe.edu/sfi/education/indexCSSS.html or summerschool@santafe.edu. 2001 SUMMER SCHOOL FACULTY Directors: SANTA FE BUDAPEST Ray Goldstein, U. Arizona Imre Kondor, Eotvos Univ. Melanie Mitchell, SFI Melanie Mitchell, SFI Partial List of Lecturers: SANTA FE BUDAPEST Elizabeth Bradley, U. Colorado Imre Kondor, Eotvos Univ. Thomas Carter, Cal. State U. Andras Kroo, Renyi Inst. Math. Sean Elicker, U. New Mexico Melanie Mitchell, SFI Ray Goldstein, U. Arizona Cristopher Moore, U. New Mexico Thomas Halsey, Exxon Research Mark Newman, SFI Laura Landweber, Princeton Zoltan Racz, Eotvos Univ. Seth Lloyd, MIT Grzegorz Rozenberg, Leiden U. Melanie Mitchell, SFI Hava Siegleman, Technion Harold Morowitz, George Mason U. Erik Schultes, MIT Cosma Shalizi, SFI Peter Schuster, Univ. Vienna Ken Steiglitz, Princeton Eors Szathmary, Eotvos Univ. Eors Szathmary, Eotvos Univ. Gabor Vattay, Eotvos Univ. Koen Visscher, U. Arizona Tamas Vicsek, Eotvos Univ. Lance Williams, U. New Mexico Erik Winfree, MIT ------------------------------ Date: Thu, 16 Nov 2000 02:40:01 +0000 From: Vitorino Ramos Subject: 4 new Papers Hello: Four new publications (2000) are now available Online at the site: http://alfa.ist.utl.pt/~cvrm/staff/vramos/index.html Follow the link [2000] and the respective paper number to see the abstracts and the link to the PDF files. Here are the Refs.: Vitorino Ramos, Artificial Neoteny in Evolutionary Image Segmentation, Proc. of SIARP'2000 - 5th IberoAmerican Symposium on Pattern Recognition, Fernando Muge, Moisés Piedade & R. Caldas Pinto (Eds.), ISBN 972-97711-1-1, pp. 69-78, Lisbon, Portugal, 11-13 Sep. 2000. Vitorino Ramos, Genetic Clustering Towards Image Segmentation, Proc. of SIARP'2000 - 5th IberoAmerican Symposium on Pattern Recognition, Fernando Muge, Moisés Piedade & R. Caldas Pinto (Eds.), ISBN 972-97711-1-1, pp. 61-68, Lisbon, Portugal, 11-13 Sep. 2000. Vitorino Ramos, Fernando Muge, Map Segmentation by Colour Cube Genetic K-Mean Clustering, Proc. of ECDL'2000 - 4th European Conference on Research and Advanced Technology for Digital Libraries, J. Borbinha and T. Baker (Eds.), ISBN 3-540-41023-6, Lecture Notes in Computer Science, Vol. 1923, pp. 319-323, Springer-Verlag -Heidelberg, Lisbon, Portugal, 18-20 Sep. 2000. Vitorino Ramos, Filipe Almeida, Artificial Ant Colonies in Digital Image Habitats - A Mass Behaviour Effect Study on Pattern Recognition, Proceedings of ANTS'2000 - 2nd International Workshop on Ant Algorithms (From Ant Colonies to Artificial Ants), Marco Dorigo, Martin Middendorf & Thomas Stüzle (Eds.), pp. 113-116, Brussels, Belgium, 7-9 Sep. 2000. I Hope you enjoy, Best Regards, Vitorino Eng. Vitorino J. Castelo Ramos MSc / PhD Research Fellow on Artificial Intelligence & Image Analysis CVRM / IST (Lisbon - PORTUGAL) MAIL - mailto:vitorino.ramos@alfa.ist.utl.pt URL - http://alfa.ist.utl.pt/~cvrm/staff/vramos/index.html URL - http://www.terravista.pt/MeiaPraia/1323 ------------------------------ Date: Thu, 16 Nov 2000 10:37:28 +0530 (IST) From: Sanghamitra Bandyopadhyay Subject: CFP: IETE CALL FOR PAPERS Special issue in IETE Journal of Research on Evolutionary Computation in Engineering Sciences Evolutionary Computation (EC) comprises several techniques for search and optimization in large and complex domains. Its successful application to different engineering fields has made them immensely popular in recent times. This special issue of IETE Journal of Research on ``Evolutionary Computation" in Engineering Sciences is intended for reporting the substantial findings and knowledge base generated in these areas for wider dissemination among the science and technology community. Papers on, but not limited to, the following topics, containing original research, new concepts, novel approaches, theoretical studies and in-depth understanding of the subjects, are invited in the field of evolutionary computation. Pattern Recognition Data Mining Image Processing and Computer Vision Case Based Reasoning Machine Learning Multiobjective Optimization VLSI System Design Hardware/Software Codesign Distributed System Embedded Systems Robotics Mobile Computing Real-life Applications Multi Agent Systems Prof. Sankar K. Pal Guest Editor (Special Issue) IETE Journal of Research Distinguished Scientist and Head Machine Intelligence Unit Indian Statistical Institute 203, B. T. Road, Calcutta - 700 035, India Email : sankar@isical.ac.in Ph: 91 33 577 8085 Ext. 3101 Fax: 91 33 577 6680 Dr. Ujjwal Maulik Dr. Sanghamitra Bandyopadhyay * Co-Guest Editor (Special Issue) Co-Guest Editor (Special Issue) IETE Journal of Research IETE Journal of Research Dept. of Comp. Sc. & Tech. Machine Intelligence Unit Kalyani Govt. Engg. College Indian Statistical Institute Kalyani - 741 235, India 203, B.T. Road, Calcutta - 700 035, India Email: ujjwal_maulik@kucse.wb.nic.in Email: sanghami@isical.ac.in Ph: 91 33 582 6680 Ph: 91 33 577 8085 Ext. 3114 Fax: 91 33 582 6680 Fax: 91 33 577 6680 Three copies of the paper may be sent to Dr. Sanghamitra Bandyopadhyay by February 28, 2001. * Editor to whom all correspondence should be addressed Dr. Sanghamitra Bandyopadhyay email: sanghami@www.isical.ac.in Lecturer Tel: (91)(33)577 8085 extn 3114 Machine Intelligence Unit Fax: (91)(33)577 6680 Indian Statistical Institute 203 B. T. Road, Calcutta 700035 West Bengal, India. ------------------------------ Date: Thu, 16 Nov 2000 17:20:48 -0600 From: Franz Rothlauf Subject: CFP: ROPNET-2001 Workshop at GECCO-2001 1st Call for participation ROPNET-2001 REPRESENTAITONS AND OPERATORS FOR NETWORK PROBLEMS Bird-of-a-feather Workshop at the Genetic and Evolutionary Computation Conference 2001 ( GECCO-2001 ) San Francisco, California, July 7 - 11, 2001 (Saturday - Wednesday) organized by Franz Rothlauf WORKSHOP SUMMARY Finding good solutions for network design problems is important in many fields such as telecommunications, computer, backbone access, transportation and distribution networks. Over the last years genetic algorithms have been applied with success to a wide variety of these different problems. One of the major design issues is how the network could be represented as an artificial chromosome and what kind of operators could be defined on the chromosome. The workshop is intended to give an overview over the existing approaches and to discuss various representations and operators in the context of genetic and evolutionary computation. It should compare theoretical properties and empirical performance characteristics of different representations and operators and try to find explanations for performance differences of a genetic algorithm. The workshop will be focused on representations and operators for problems, but it welcomes interesting contributions to encoding issues that are meaningful for network representations. PARTICIPATION Presentations will be selected according to the submitted 10-page papers which will be reviewed by at least two members of the international program committee. Accepted papers will be available in electronic form before the workshop. Abbreviated versions of the papers will be later published in the workshop proceedings. The length of each paper will be determined by the number of accepted papers. For more detailed submission guidelines and recent updates, see the workshop pages at http://btw6x2.oec.uni-bayreuth.de/ropnet/ IMPORTANT DATES (subject to change) Paper submission deadline: March 1, 2001 Decisions will be mailed by: April 1, 2001 Submissions of camera-ready papers: April 20, 2001 WORKSHOP CHAIR Franz Rothlauf Department of Information Systems University of Bayreuth 95445 Bayreuthn Germany rothlauf@uni-bayreuth.de Tel/Fax: +49 921 55 2819, +49 921 55 2216 Illinois Genetic Algorithms Laboratory 104 S. Mathews Ave. University of Illinois at Urbana-Champaign Urbana, IL 61801 rothlauf@illigal.ge.uiuc.edu ATTENDANCE Attendance to the workshop is open to all GECCO attendees. Further information will be posted on the workshop web pages ( http://btw6x2.oec.uni-bayreuth.de/ropnet/ ) as soon as it becomes available. We are looking forward to your participation at the first workshop ROPNET-2001 which is a great opportunity to meet and discuss the covered topics for researchers in this area of research as well as the ones who would like to learn more about representations and networks. ------------------------------ Date: Thu, 16 Nov 2000 21:32:08 -0700 From: "Nadine Gisler" Subject: Soft Computing and Intelligent Systems Call FOR PAPER Fourth International ICSC Symposia on SOFT COMPUTING AND INTELLIGENT SYSTEMS FOR INDUSTRY June 26-29, 2001 Paisley, Scotland, U.K. General Information PURPOSE OF SOCO/ISFI 2001 The twin conferences, Soft Computing (SOCO 2001) and Intelligent Systems for Industry (ISFI 2001) are intended to cover the field of "soft computing" from pure blue-sky research (SOCO) to prototypes and applications of soft computing. Soft computing has become a term embracing artificial neural networks, evolutionary algorithms, belief networks, fuzzy sets and logics, etc. (A fuller list of topics appears below). AIM OF SOCO 2001 AND ISFI 2001 SOCO 2001 aims to be of broad interest to engineers, computer scientists and all who use such technologies. It will be a forum for the -Dissemination of new research in the field of soft computing. -Introduction of application-oriented researchers to leading edge new research. ISFI 2001 will encourage practitioners and researchers from industry, commerce, education and governments to submit existing applications of soft computing either as technical papers or as demonstrations. ISFI 2001 aims to be a forum for the -Dissemination of results on new applications in this field. -Introduction of pure research oriented personnel to applications of soft computing. Symposium Topics (SOCO'2001) Soco'2001 will include contributions on long term research (theory development, enhanced approaches, formal methods comparisons, applications, etc.) in the area of soft-computing. Contributions are sought in areas based on the list below, which is indicative only. Neural Networks Fuzzy Logic Rough Sets Genetic Algorithms and Evolutionary Computing Chaos Theory Al and Expert Systems Probabilistic Reasoning, belief nets Machine learning Learning Algorithms and Intelligent Control Pattern Recognition and Image Understanding Distributed Intelligence Self-Organizing Systems Fuzzy Databases and Information Retrieval Educational Aspects of Soft Computing Symposium Topics (ISFI'2001) ISFI'2001 will include contributions in the research area of Soft Computing Application and, more general, related to medium-to-short term and application driven developments Advanced Information Technology and Industrial Intelligent Technology. Particular emphasis will be laid on industrial realization, experimental application, application methodology development and/or formalization, quantitative and qualitative problem modelling. Contributions are sought mainly in the areas based on the list below: -Industrial Area: Commerce, Energy, Transportation, Services, Medicine etc. -High-Tech Area: Innovative Control and Diagnostics, Computer Vision, Robotics and Remote Sensing, Speech Recognition and Machine Translation, Mechatronics, etc. -Green-tech Area: Intelligent Resource Management, Intelligent Pollutant Management, User Behavior Modelling, Intelligent Traffic Control, etc. Important Dates Submission Deadline November 30, 2000 Notification of Acceptance January 31, 2001 Delivery of Full Papers March 15, 2001 SOCO/ISFI'2001 International Congress June 26-29, 2001 Further Information Please contact: ICSC International Computer Science Conventions 5101C - 50 Street, Wetaskiwin, Alberta T9A 1K1 / Canada E-mail: operating@icsc.ab.ca or planning@icsc.ab.ca Phone: +1-780-352-1912 / Fax: +1-780-352-1913 or for specific scientific information contact the congress chair: Prof. Colin Fyfe (General Chair) University of Paisley Computing & Information Systems High Street Paisley PA1 2DE Scotland, U.K. Email: fyfe0ci@paisley.ac.uk Fax: +44-141-848-3542 Prof. Lorenzo Moreno (Vice-Chair) University La Laguna Tenerife Edificio de Fisica y Matematicas Av. Astrofisico Francisco Sánchez S/N E - 38071 La Laguna (Tenerife) Spain Email: lmoreno@ull.es Fax: 34-22-603217 ------------------------------ Date: Fri, 17 Nov 2000 09:59:20 +0100 From: Wolfgang Banzhaf Subject: Quote from review Hello: It has come to my attention that a comment of one reviewer of a rejected manuscript, originally submitted to GPEM, has been cited by the author for advertising purposes. I have to say that this comment needs to be seen in the context of the review, and cannot be judged as it stands. Recommended by three reviews of extraordinary detail, the paper has been rejected by Genetic Programming and Evolvable Machines. As the author concedes - it was rejected by NATURE, too. These are the facts, and I don't consider them to be a recommendation of the manuscript. Wolfgang Banzhaf Editor-in-Chief Genetic Programming and Evolvable Machines ------------------------------ Date: Sun, 19 Nov 2000 18:16:10 -0600 From: Martin Pelikan Subject: IlliGAL New Technical Reports Announcement (November, 2000) The Illinois Genetic Algorithms Laboratory (IlliGAL) is pleased to announce the publication of the following new technical reports and software. Most IlliGAL technical reports, as well as reprints of other publications, are available in hardcopy and can be ordered from the IlliGAL librarian, (see below for ordering information). The technical reports in this announcement are also available electronically on our ftp and WWW servers (see the end of this announcement for ftp and WWW access instructions). (1) NEW TECHNICAL REPORTS IlliGAL Report No 2000028 Mining Oblique Data with XCS Stewart W. Wilson Abstract: The classifier system XCS was investigated for data mining applications where the dataset discrimination surface (DS) is generally oblique to the attribute axes. Despite the classifiers' hyper-rectangular predicates, XCS reached 100% performance on synthetic problems with diagonal DS's and, in a train/test experiment, competitive performance on the Wisconsin Breast Cancer dataset. Final classifiers in an extended WBC learning run were interpretable to suggest dependencies on one or a few attributes. For data mining of numeric datasets with partially oblique discrimination surfaces, XCS shows promise from both performance and pattern discovery viewpoints. IlliGAL Report No 2000029 A note on using genetic and evolutionary algorithms for multi-periodcommunication network optimisation Franz Rothlauf, Christian Grasser This paper addresses the optimization of telecommunication networks for a multi-period horizon. Four heuristics are presented to cope with the problem to minimize the overall costs for the network over several periods. For the minimization of cost we use a simple genetic algorithm (GA). It is adapted in different ways to the special structure of the network problem. Even in the single-period case, the stated problem is hard to solve. For solving the multi-period problem we have two possible choices: Firstly, all periods could be solved synchronously (in parallel). Secondly, the different periods are optimized step by step (serially). With serial optimization, the algorithm could fail in finding the global minimum, but the computational effort for the parallel optimization is so much higher that it can hardly be used other than in small test problems. In addition to this, the solutions for the periods are very similar, meaning that the parallel optimization has to detect a lot of redundant information. To optimize the overall costs serially we present four different approaches. The first, and most simple optimizes the structure of the network for each period independently of the solutions for other periods. The second approach optimizes only the structure for the first period, and the structure of the network is not changed for the following periods. Only the capacities of the links are scaled up according to the necessary demands. The third approach optimizes serially the structure of the networks for the different time periods starting from the first. For the fitness of the individuals, the overall cost of the network, including the cost for changing the lines between the periods, is used. Finally we propose an extension of the third approach. In an initial step, all time periods are optimized sequentially and independently from each other. After the first run over the whole planning horizon, we will pick out periods randomly and optimize this period with respect to the previous and next periods. We believe that this extension leads to a more stable and robust solution of the network design problem. We present some results for the first three approaches for a specific real-world problem. A short investigation of the performance shows that we gain the best results by using the third approach. IlliGAL Report No 2000030 The parameter-less genetic algorithm: Rational and automated parameter selection for simplified genetic algorithm operation Fernando G. Lobo Abstract: Genetic algorithms (GAs) have been used to solve difficult optimization problems in a number of fields. One of the advantages of these algorithms is that they operate well even in domains where little is known, thus giving the GA the flavor of a general purpose problem solver. However, in order to solve a problem with the GA, the user usually has to specify a number of parameters that have little to do with the user's problem, and have more to do with the way the GA operates. This dissertation presents a technique that greatly simplifies the GA operation by relieving the user from having to set these parameters. Instead, the parameters are set automatically by the algorithm itself. The validity of the approach is illustrated with artificial problems often used to test GA techniques, and also with a simplified version of a network expansion problem. IlliGAL Report No 2000031 Network random keys - a tree network representation scheme for genetic and evolutionary algorithms Franz Rothlauf, David E. Goldberg, Armin Heinzl Abstract: When using genetic and evolutionary algorithms for the design of network structures, a good choice of the representation scheme for the construction of the genotype is important for the performance of the algorithm. One of the most common representation schemes for networks is the characteristic vector representation. However, with encoding tree networks, and using crossover and mutation, invalid individuals occur that are either under- or over-specified.% and need some kind of repair mechanism. When constructing the offspring, or repairing the invalid individuals that do not represent a tree, it is not possible to distinguish between the importance of the links which should be used. These problems can be overcome by transferring the concept of random keys from scheduling and ordering problems, to the encoding of tree networks. This paper investigates the performance of a simple genetic algorithm (SGA) using network random keys (NetKeys) for a One-Max-Tree and a real-world problem. The comparison between the network random keys and the characteristic vector encoding shows that despite the effects of stealth mutation that favors the characteristic vector representation a selectorecombinative GA with NetKeys has some advantages for small and easy optimization problems. As soon as it comes to more complex problems, a GA with network random keys outperforms significantly a GA using characteristic vectors. The paper shows that random keys can be used for the encoding of tree networks, and that GAs using network random keys are able to solve complex tree network problems much faster than when using the characteristic vector. Users should be encouraged to use network random keys for the representation of tree networks. IlliGAL Report No 2000032 The Anticipatory Classifier System and Genetic Generalization Martin Butz, David E. Goldberg, Wolfgang Stolzmann Abstract: The anticipatory classifier system (ACS) combines the learning classifier system framework with the learning theory of anticipatory behavioral control. The result is an evolutionary system that builds an environmental model and further applies reinforcement learning techniques to form an optimal behavioral policy in the model. After providing some background as well as outlining the objectives of the system, we explain in detail all involved current processes. Furthermore, we analyze the deficiency of over-specialization in the anticipatory learning process (ALP), the main learning mechanism in the ACS. Consequently, we introduce a genetic algorithm (GA) to the ACS that is meant for generalization of over-specialized classifiers. We show that it is possible to form a symbiosis between a directed specialization and a genetic generalization mechanism achieving a learning mechanism that evolves a complete, accurate, and compact description of a perceived environment. Results in three different environmental settings confirm the usefulness of the genetic algorithm in the ACS. Finally, we discuss future research directions with the ACS and anticipatory systems in general. IlliGAL Report No 2000033 Progress Toward Linkage Learning in Real-Coded GAs with Simplex Crossover Shigeyoshi Tsutsui, David E. Goldberg, Kumara Sastry In recent years, many researchers have concentrated on using real-valued genes in genetic and evolutionary algorithms (GEAs). Previous studies have proposed simplex crossover (SPX) for real-coded GAs. SPX has several good characteristics and works well on various test functions. However, SPX fails on functions that consist of tightly linked sub-functions. On those functions, SPX should be applied on each tightly linked group of parameters. In this paper, we propose a method of linkage identification in real-coded GAs with SPX and evaluate it using several test functions. The mechanism works well on many of the test functions used. We also discuss difficulties with the proposed method on more complex test functions and show possible solutions to the problems. IlliGAL Report No 2000034 Ordering messy genetic algorithm in C++ Dimitri Knjazew The OmeGA 1.0 implementation of the ordering messy genetic algorithm in C++ is freely available from the IlliGAL anonymous ftp-site. The implementation covers the basic features of the OmeGA and provides three permutation problems for testing purposes. This paper explains how to download, compile, and run the code. (2) NEW SOFTWARE: 1. C++ implementation of the Ordering Messy Genetic Algorithm (OMEGA) Dimitri Knjazew Available at ftp://ftp-illigal.ge.uiuc.edu/pub/src/OmeGA/omega.tar.gz 2. New version 1.1 of the BOA with decision graphs Martin Pelikan Available at ftp://ftp-illigal.ge.uiuc.edu/pub/src/decisionGraphBOA/dBOA1-1.tar.Z RETRIEVAL/ORDERING: The above IlliGAL reports and publications, along with other publications and source code, are available electronically via FTP or WWW, or as hardcopy directly from us: FTP: ftp ftp-illigal.ge.uiuc.edu login: anonymous password: (your email address) cd /pub/papers/IlliGALs (for reports) or cd /pub/papers/Publications (for preprints) or cd /pub/src (for GA and classifier system source code) binary get 99022.ps.Z (for example) Please look at the README files for explanations of what the file names mean. IlliGAL reports are all compressed postscript files. WWW: To access the IlliGAL home page, open http://www-illigal.ge.uiuc.edu/ HARDCOPY: You can also order hardcopy versions of most IlliGAL publications Use the order form in the web or request them directly (by IlliGAL number or title) from the IlliGAL librarian: Internet: library@illigal.ge.uiuc.edu Phone: 217/333-2346 Fax: 217/244-5705 Surface mail: IlliGAL Librarian Department of General Engineering 117 Transportation Building 104 South Mathews Avenue Urbana, IL 61801-2996 USA When ordering hardcopy, please include your surface mail address! Martin Pelikan Illinois Genetic Algorithms Laboratory University of Illinois at Urbana Champaign 117 Transportation Building 104 S. Mathews Avenue, Urbana, IL 61801 tel: (217) 333-2346, fax: (217) 244-5705 ------------------------------ Date: Mon, 20 Nov 2000 16:40:26 +0000 (GMT) From: Simon Parsons Subject: Agents 2001 Call for Tutorials, Workshops and Demos CALL FOR TUTORIALS, WORKSHOPS AND DEMONSTRATIONS Fifth International Conference on Autonomous Agents (Agents 2001) Montreal, Canada, Monday 28 May - Friday 1 June 2001 http://autonomousAgents.org/2001 The organising committee for Autonomous Agents 2001 invites proposals for workshops and tutorials to be held on 28th and 29th May, just before the main conference. December 8, 2000 Deadline for Workshop proposals December 8, 2000 Deadline for Tutorial proposals The conference will also feature software and robot demonstrations, and submissions from those interested in demonstrating their systems are invited. February 23, 2001 Deadline for Robot Demonstrations February 23, 2001 Deadline for Software Demonstrations More details on workshops, tutorials and demonstrations may be found on the conference web site. ------------------------------ Date: Tue, 21 Nov 2000 09:51:25 +1100 (EST) From: Congress on Evolutionary Computation Subject: CEC 2001 CFP - Revised Deadline Congress on Evolutionary Computation 2001 (CEC2001) May 27- 30, 2001, COEX Center, Seoul, Korea Submission Deadline: December 15, 2000 (new) Homepage: http://cec2001.kaist.ac.kr/ The 2001 Congress on Evolutionary Computation (CEC2001) will bring together rese archers to exchange and report recent progress in evolutionary computation and i ts application to real-world problems. CEC2001 is jointly sponsored by the IEEE Neural Networks Council, the Evolutionary Programming Society, and the Instituti on of Electrical Engineers (IEE), and the Institute of Control, Automation and Systems Engineers, Korea (ICASE). TOPICS OF INTEREST CEC2001 welcomes submissions on all aspects of evolutionary computation, includi ng but not limited to evolutionary computation theory, evolutionary computation methodology, and evolutionary computation applications. TUTORIALS Tutorials will provide a means for senior researchers to present an overview of a field related to evolutionary computation. The current tutorial program includ es: - Introduction to Evolutionary Computation (David B. Fogel) - Evolutionary Search Distributions (Heinz Muehlenbein) - Evolutionary Computation: A Unified View (Ken DeJong) - Artificial Immune Systems (Jon Timmis) - Molecular Computing (Jian-Qin Liu) - Evolutionary Neural Networks (Xin Yao) - Genetic Programming Theory (Riccardo Poli) - Evolutionary Learning and Generalization (Ibrahim Kuscu) - Building a PC Cluster (Tomo Hiroyasu) - Evolutionary Hardware (tentative) - Evolutionary Constraint Optimization (tentative) - Theory of Evolutionary Computation (to be announced) SPECIAL SESSIONS CEC2001 special sessions are to be organized around specific topics in order to encourage in-depth discussion as an integral part of the CEC2001. The list of ac cepted special sessions and their organizers is as follows: - Natural and Physical Science Applications (Gary Fogel) - Image, Speech & Pattern Recognition Applications (Tuan Pham) - New Paradigms (Eugene Eberbach) - Design Automation (Giovanni Squillero) - Molecular Electronics and Evolutionary Moleware (Jian-Qin Liu) - Evolutionary Multiobjective Optimization (David Corne) - Surface and Curve Modeling & Optimization with Evolutionary Computation (Bernh ard Sendhoff ) - Evolving Neural Networks (Shu-Hung Leung) - Scheduling (E. K. Burke) - Grammars in Evolutionary Computation (Bob McKay) - Particle Swarm Optimization (Yuhui Shi) - Molecular Evolutionary Computing (Byoung-Tak Zhang) - Intelligent Agents (Toshio Okamoto) COMPETITIONS CEC2001 features interesting competitions for which the winners will be awarded and the certificates will be given. For now the 5 competitions are announced on the web as follows: - Checkers Competition - Machine Learning Problem - 2D Design Optimization - 3D Design Optimization - Evolutionary Art and Design IMPORTANT DATES December 15, 2000: Deadline for Paper Submission February 15, 2001: Notification of Acceptance March 15, 2001: Camera-ready Papers Due May 27, 2001: Tutorials & Workshops May 28-30, 2001: Technical Sessions CONTACT POINTS Further details and up-to-date information on CEC2001 can be found at http://cec2001.kaist.ac.kr. Further inquiries can be made at: Tel: +82-42-472-7458 Fax: +82-42-472-7459 E-mail: cec2001@kaist.ac.kr Jong-Hwan Kim, KAIST Gary Fogel, Natural Selection Inc. Ibrahim Kuscu, Univ. of Surrey Byoung-Tak Zhang, Seoul Nat¡¯l Univ. ------------------------------ Date: Tue, 21 Nov 2000 23:07:14 -0200 (EDT) From: Renato Krohling Subject: IA and optimization I am looking for pointers to papers combining intelligent agents for optimization and evolutionary algorithms. I appreciate any help. Thanks Renato Email: renato@ele.ufes.br or renato@lse.uni-sb.de ------------------------------ Date: Wed, 22 Nov 2000 05:14:15 -0700 From: "Nadine Gisler" Subject: Welcome to the First ICSC Congress on Neuro-Fuzzy NF'2002 INTERNATIONAL COMPUTER SCIENCE CONVENTIONS Head Office: 5101C-50 Street, Wetaskiwin AB, T9A 1K1, Canada (Phone: +1-780-352-1912 / Fax: +1-780-352-1913) Email: or / Web-Site: http://www.icsc.ab.ca Welcome to the First International ICSC Congress on Neuro-Fuzzy NF'2002 to be held at The Capitolio de la Habana, Cuba January 15 - 18, 2002 We are sending this message requesting papers for this conference. http://www.icsc.ab.ca/NF2002.htm Introduction: During the past decade, paradigms and benefits from neuro fuzzy systems (NF) have been growing tremendously. Today, not only does NF solve scientific problems, but its applications are also appearing in our daily lives. In order to discuss the state of the art in NF and the future of these exciting topics; we are honored to invite you to Neuro-Fuzzy 2002. We believe it will be an excellent opportunity to share our knowledge on NF and contribute to its development in the next century. This major international conference will be held in a very enjoyable location: Havana, the Capital of Cuba, where we hope you will experience the famous Cuban hospitality. Topics suggested (not limited to): - Advanced Neuro and Fuzzy Paradigms - Data Granulation and Fuzzy Rule Extraction - Advanced Training Algorithms - Evolutionary Computation (GA, GP, ET) and Graphical Models - Chaotic Behavior and Fractals Applications in signal processing, control, robotics, etc. Of particular interest are applications from the following fields: Sound and image processing, pattern recognition, image understanding, feature binding, perception, sensor fusion, controller design, state observation, motor control, mobile robotics, autonomous navigation, deliberation and planning, active anchoring, gain-scheduling, fault detection, hardware solutions, data mining, financing, e-commerce. IMPORTANT DATES Submission Deadline: May 31, 2001 Notification of Acceptance: August 15, 2001 Delivery of Final Manuscripts: October 31, 2001 Conference NF'2002: January 15/18, 2002 CONGRESS ORGANIZER ICSC International Computer Science Conventions NAISO Natural and Artificial Intelligence Systems Organizations 5101C - 50 Street Wetaskiwin AB, T9A 1K1 / Canada Phone: +1-780-352-1912 Fax: +1-780-352-1913 Email Operating Division: operating@icsc.ab.ca Email Planning Division: planning@icsc.ab.ca GA-List@aic.nrl.navy.mil ICSC ------------------------------ Date: Thu, 23 Nov 2000 18:03:40 +0100 (MET) From: Bernhard Sendhoff Subject: CEC 2001 Competitions CALL FOR PARTICIPATION ** Competitions ** Congress on Evolutionary Computation CEC 2001 Seoul, Korea May 27-30, 2001 http://cec2001.kaist.ac.kr/ The CEC2001 will include a competition session. The aim of this session is to compare different algorithmic approaches to one problem, which is shared among all participants. In order to enhance the interest of prospective participants we try to organise special sessions alongside the different topics of the competitions. Additionally, the winner of the 2D/3D design competition and of the machine learning competition will receive free registration to the 2002 World Congress on Computational Intelligence in Hawaii (many thanks to David Fogel). Some companies will sponsor the CEC2001 competition and offer additional prizes (ca. 200 US$) for the winners. To summarize the benefits for the participants: * Awarding of the winners together with short presentations during the CEC2001 competition session. * Some competitions will offer free WCCI 2002 registration to winners. * Additional cash prices for some competitions. If you have any questions regarding details of the competitions, please consult the web page at http://cec2001.kaist.ac.kr/ or contact one of the competition chairs. Competitions * Checkers competition * Machine Learning problem * 2D design optimisation (alongside special session "Surface and Curve Modelling with Evolutionary Computation") * 3D design optimisation (alongside special session "Surface and Curve Modelling with Evolutionary Computation") * Evolutionary art and design Important dates 31.03.2001 - submission deadline for both design optimisation competitions CEC2001 Competition chairs Dr. Simon Lucas Dept of Electronic Systems Engineering University of Essex Great Britain sml@essex.ac.uk Dr. Bernhard Sendhoff Future Technology Research Division HONDA R&D Europe GmbH Germany bs@el-tec.de ------------------------------ Date: Thu, 23 Nov 2000 18:10:02 +0100 (MET) From: Bernhard Sendhoff Subject: CEC 2001 - Special Session on Surface and Curve Modelling CALL FOR PAPERS/PARTICIPATION Special Session Surface and Curve Modelling & Optimisation with Evolutionary Computation Congress on Evolutionary Computation CEC 2001 Seoul, Korea May 27-30, 2001 http://cec2001.kaist.ac.kr/ INTRODUCTION The 2001 Congress on Evolutionary Computation (CEC2001) will highlight recent research covering all forms of evolutionary computations while fostering discussions and cooperative progress in the evolutionary computation field. Following the tradition of CEC1999 and CEC2000, next years venue in Seoul, Korea will again contain several special sessions dedicated to a particular topic and organised by one or several researchers working on this subject. All accepted papers in the special sessions will be included in the published conference proceedings. SPECIAL SESSION "Surface and Curve Modelling & Optimisation with Evolutionary Computation" The area of surface and curve modelling & optimisation, frequently shortened to design optimisation, has recently gained considerable interest from researchers in evolutionary computation. Compared to the traditional optimisation techniques, evolutionary algorithms do not need derivative information of the systems, are shown to be robust and well suitable for multi-disciplinary optimisation. Meanwhile, there are also challenging problems remain to be solved, one of which is the high computation demand needed by the evolutionary based optimisation. This session is dedicated to the application of evolutionary computation to design optimisation. Topics include but are not limited to 1) Design of 2D or 3D objects for different applications, examples of which are: aerodynamic structures (wing shapes, turbine blades, etc.), structures for static and dynamic stability (automobile frames for crash tests), objects of everyday use (aesthetic design optimisation), multi-disciplinary optimisation (aerodynamic plus mechanic plus electrodynamic constraints). 2) Issues from evolutionary computations: the choice of the representation (splines, NURBS), the choice of the operators (self-adaptation) and the comparison of existing evolutionary approaches (ES, GA, GP). 3) The use of meta-models and their integration in the evolutionary algorithms. 4) The parallelisation of existing algorithms for design optimisation. IMPORTANT DATES December 15, 2000: Deadline for paper titles and abstracts January 15, 2001: Deadline for paper submission to special session February 15, 2001: Notification of acceptance March 15, 2001: Camera-ready papers due March 15, 2001: Early registration May 27-30, 2001: CEC 2001 conference dates For SUBMISSION and further ENQUIRES, please contact: email: Bernhard.Sendhoff@hre-ftr.f.rd.honda.co.jp bs@el-tec.de Bernhard Sendhoff Future Technology Research Division HONDA R&D Europe (Deutschland) GmbH Carl-Legien-Strasse 30 63073 Offenbach/Main Germany ------------------------------ Date: Fri, 24 Nov 2000 12:25:43 -0800 From: "John Koza" Subject: New Tech Report on Automatic Synthesis of Metabolic Pathways using GP Hello All: We have just completed a 53-page Stanford University technical report entitled "Reverse Engineering and Automatic Synthesis of Metabolic Pathways from Observed Data Using Genetic Programming and by J. R. Koza, W. Mydlowec, G. Lanza, J. Yu, and M. A. Keane. It is available as a PDF file from http://smi-web.stanford.edu/pubs/SMI_Abstracts/SMI-2000-0851.html Abstract: Recent work has demonstrated that genetic programming is capable of automatically creating complex networks (such as analog electrical circuits and controllers) whose behavior is modeled by continuous-time differential equations (both linear and non-linear) and whose behavior matches prespecified output values. The concentrations of substances participating in networks of chemical reactions are also modeled by non-linear continuous-time differential equations. This paper demonstrates that it is possible to automatically create (reverse engineer) a network of chemical reactions from observed time-domain data. Genetic programming starts with observed time-domain concentrations of input substances and automatically creates both the topology of the network of chemical reactions and the rates of each reaction within the network such that the concentration of the final product of the automatically created network matches the observed time-domain data. This paper describes how genetic programming automatically created a metabolic pathway involving four chemical reactions that takes in glycerol and fatty acid as input, uses ATP as a cofactor, and produces diacyl-glycerol as its final product. In addition, this paper describes how genetic programming similarly created a metabolic pathway involving three chemical reactions for the synthesis and degradation of ketone bodies. Both automatically created metabolic pathways contain at least one instance of three noteworthy topological features, namely an internal feedback loop, a bifurcation point where one substance is distributed to two different reactions, and an accumulation point where one substance is accumulated from two sources. ------------------------------ End of Genetic Algorithms Digest ******************************