Genetic Algorithms Digest Thursday, March 27, 1997 Volume 11 : Issue 9 - Do NOT send email or reply to gadistr@aic.nrl.navy.mil (GA List Moderator) - Send submissions (articles) to GA-List@AIC.NRL.NAVY.MIL - Send administrative (subscribe, unsubscribe, change of address, etc.,) requests 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: - A Message From the Governing Board of ISGA - Seeking work on GA-based non-hierarchical clustering - Evolution and development of ANNs - Book Announcement: 2nd Edition Li-Vitanyi on Kolmogorov Complexity - Short Course Announcement - New Home for The Genetic Programming Notebook - Help needed ---------------------------------------------------------------------- CALENDAR OF GA-RELATED ACTIVITIES: (with GA-List issue reference) ICANNGA97 Intl Conf on Artificial NNs and GAs, England (v10n16) Apr 1-4, 97 AISB97 Workshop on Evolutionary Computing, Manchester (v10n42) Apr 7-8, 97 EP97 Conf on Evolutionary Programming, Indianapolis (v10n19) Apr 13-16, 97 ICEC97 Intl Conf Evolutionary Computation, Indianapolis(v10n27) Apr 13-16, 97 KES97 Knowledge-Based Intel Electronic Systems,Australia(v10n48)May 21-23, 97 ISMB97 Intelligent Systems for Molecular Biology,Greece(v10n42) Jun 21-25, 97 WSC2 Online World Conf on Soft Computing, on the Internet(v11n2)Jun 23-27, 97 MENDEL97 Intl Mendel Conference on GAs, etc, Brno, Czech (v11n3)Jun 25-27, 97 GP97 Genetic Programming Conference, Stanford, CA (v10n45) Jul 13-16, 97 ICGA97 Intl Conf on Genetic Algorithms, East Lansing MI(v10n35) Jul 19-23, 97 MIC97 Metaheuristic Intl Conf, Sophia-Antipolis France (v10n47) Jul 21-24, 97 ECAL97 4th European Conf on Artificial Life, England (v10n36) Jul 28-31, 97 3NWGA 3rd Nordic Workshop on GAs, Helsinki, Finland (v10n43) Aug 18-20, 97 PATAT97 Intl Conf on Automated Timetabling, Toronto (v11n6) Aug 20-22, 97 IJCAI97 Workshop on Evolvable Systems, Nagoya, Japan (v11n5,6) Aug 23, 97 IMACS97 Scientific Comp, Modelling & App Math, Germany (v10n42) Aug 24-29, 97 IMACS97 Evolutionary Computation, Berlin, Germany (v10n45) Aug 24-29, 97 BCEC97 Bio-Computing and Emergent Computation, Sweden (v10n44) Sep 1-2, 97 GALESIA97 Conf on GAs in Engineering Systems, Glasgow UK (v10n36) Sep 2-4, 97 EUROMICRO97 Euromicro Wrkshp on Comp Intel, Hungary (v10n47) Sep 3-4, 97 EUFIT97 Intelligent Techniques & Soft Computing, Aachen (v10n41) Sep 8-12, 97 SOCO97 Intl ICSC Symposium on Soft Computing, France (v10n40) Sep 17-19, 97 EA97 Evolution Artificielle, EMA-EERIE, Nimes, France (v11n4), Oct 23-27, 97 Evol Computation for Industrial Applications,New Zealand (v11n3)Nov 24-28, 97 EuroGen97 Short course GAs & ESs / Comp Sci & Eng (v11n5) Nov 28 - Dec 5, 97 ACDM98 Adaptive Comp in Design & Manufacture, Plymouth (v11n3) Apr 21-23, 98 ISORA98 Learning Cyclic Control/Behavior in Robots,Alaska (v11n8)May 10-14,98 http://www.aic.nrl.navy.mil/galist/info/conferences/CONFERENCES.html has more information on the above conference activities. Send announcements of other activities to GA-List@aic.nrl.navy.mil. ------------------------------ From: darrell whitley Date: Fri, 21 Mar 1997 13:55:29 -0700 (MST) Subject: A Message From the Governing Board of ISGA The following message deals with the governance of the International Society for Genetic Algorithms (ISGA) and solicits proposals for the 1998 Foundations of Genetic Algorithms workshop. THE 1997 GOVERNING BOARD ELECTIONS In 1997, three seats currently held by R. Belew, J. Holland and K. De Jong will become available on the ISGA Governing Board. Nominations of candidates to be placed on the ballot can be made to the nomination committee: S. Forrest, D. Whitley and M. Vose Recommendations should be made before June 1, 1997. The names of the candidates will be announced on Genetic Algorithm Digest prior to ICGA-97. Ballots will be available as part of the registration packet at ICGA and votes can be cast during the conference or during the business meeting at ICGA-97. The other three current members of the 9 member governing board are Pete Angeline, Nick Radcliffe and Hans-Paul Schwefel. If anyone has comments about the organization of ISGA, the operation of the Governing Board, or any other issue concerning the operation of ISGA, ICGA, or FOGA, please attend ICGA-97 and the business meeting. Individuals may also communicate directly with members of the Governing Board. Motions concerning the governance of ISGA can be made and voted on at the ISGA business meeting held at ICGA-97. The main business of ISGA is running the International Conference on Genetic Algorithms (ICGA) and the Foundations of Genetic Algorithms workshop (FOGA). An immediate issue before the Governing Board concerns the arrangements for FOGA-98. CALL FOR PROPOSALS: FOGA-5 We solicit proposals to host FOGA-5 in 1998. The Foundations of Genetic Algorithms workshop is designed to be a theory workshop with limited participation (50 to 75 individuals). Papers submitted to FOGA should be theoretical in nature or have some theoretical relevance. For past FOGA workshops, 1 or 2 individuals have taken care of all aspects of organizing and hosting FOGA as well as serving as editor(s) of the proceedings. However, if anyone wishes to take on the role of General Chair and/or Program Chair they may wish to organize and run FOGA in a different manner. We do want to keep the general structure and orientation of the FOGA workshop unchanged. Individuals interested in being a local host for FOGA or in being Chair for FOGA can obtain more information by contacting D. Whitley whitley@cs.colostate.edu (970) 493-7265 All proposals to the Governing Board should be made before May 1, 1997. ------------------------------ From: Philip Resnik Date: Wed, 19 Mar 1997 18:02:44 -0500 (EST) Subject: Seeking work on GA-based non-hierarchical clustering Hello -- I'd be grateful for pointers to work on the use of genetic algorithms (or related stochastic optimization techniques) in non-hierarchical clustering, i.e. the problem of assigning each of a set of items {i_1,...,i_n} to one of a set of clusters {C_1,...,C_m}, given only a distance (or similarity) matrix or function Dist(i_j,i_k). A particular feature of interest is the automatic determination of the appropriate number of clusters, either statically as a pre-processing step or dynamically over the run of the algorithm. I have already located some possibly relevant pointers, including - a paper by document clustering by Gareth Jones et al., - several references to "fuzzy clustering" that are of questionable relevance (I need discrete clusters for my application, though I might consider fuzzy clusters at some future point) - references to several papers by Faulkenauer involving "grouping" Comments on the relevance of this work, if you're familiar with it, will help, and I'd be very grateful for any other suggestions. If people reply to me personally rather than using list bandwidth, I'd be happy to post a summary. Philip Philip Resnik, Assistant Professor Department of Linguistics and Institute for Advanced Computer Studies 1401 Marie Mount Hall Phone : (301) 405-6760 University of Maryland Fax : (301) 405-7104 College Park, MD 20742 USA E-mail: resnik@umiacs.umd.edu ------------------------------ From: kodjaba@biologie.ens.fr (Jerome KODJABACHIAN) Date: Thu, 20 Mar 1997 17:34:12 +0100 (MET) Subject: Evolution and development of ANNs The following papers can be downloaded from the AnimatLab's Home Page: http://www.biologie.ens.fr/AnimatLab J. Kodjabachian AnimatLab Departement de Biologie Ecole Normale Superieure Paris, FRANCE kodjaba@wotan.ens.fr ===== Evolution and Development of Modular Control Architectures for 1-D Locomotion in Six-Legged Animats. J. Kodjabachian & J.-A. Meyer Abstract: An evolutionary approach is used to design neural control architectures for six-legged animats. Using a geometry-oriented variation of the cellular encoding scheme and syntactic constraints that reduce the size of the genetic search space, the developmental programs of straight locomotion controllers are first evolved. One such controller is then included as the first module in a larger architecture, in which a second neural module is evolved and develops connections to the first one, so as to set locomotion on or off according to tonic or phasic external control signals. Such an incremental approach should prove useful to the automatic design of relatively complex control architectures that might, in particular, implement some cognitive abilities over and above mere stimulus-response mechanisms. Keywords: Evolution, Development, Dynamical Neural Networks, SGOCE, Hexapod Locomotion. ==== Evolution and Development of Neural Networks Controlling Locomotion, Gradient-Following, and Obstacle-Avoidance in Artificial Insects. J. Kodjabachian & J.-A. Meyer Abstract: This paper describes how the SGOCE paradigm has been used to evolve developmental programs capable of generating neural networks that control the behavior of simulated insects. This paradigm is characterized by an encoding scheme, by an evolutionary algorithm, and by an incremental strategy that are described in turn. The additional use of an insect model equipped with 6 legs and two antennae made it possible to generate control modules that allowed to successively add gradient-following and obstacle-avoidance capacities to walking behavior. The advantages of this evolutionary approach, together with directions for future work, are discussed. Keywords: SGOCE Paradigm, Recurrent Neural Networks, Leaky Integrators, Genetic Programming, Animats. ------------------------------ From: Paul.Vitanyi@cwi.nl Date: Wed, 19 Mar 1997 15:43:41 +0100 Subject: Book Announcement: 2nd Edition Li-Vitanyi on Kolmogorov Complexity [ WMS: Normally this would fall outside the scope of GA-List, but given our extensive discussion of the NFL theorems and Kolmogorov complexity last year (see v10n*) I thought this might be of interest to some of us. ] Ming Li and Paul Vitanyi, AN INTRODUCTION TO KOLMOGOROV COMPLEXITY AND ITS APPLICATIONS, REVISED AND EXPANDED SECOND EDITION, Springer-Verlag, New York, 1997, xx+637 pp, 41 illus. Hardcover /ISBN 0-387-94868-6 (Graduate Texts in Computer Science Series) Written by two experts in the field, this is the only comprehensive and unified treatment of the central ideas and their applications of Kolmogorov complexity---the theory dealing with the quantity of information in individual objects. Kolmogorov complexity is known variously as `algorithmic information', `algorithmic entropy', `Kolmogorov-Chaitin complexity', `descriptional complexity', `shortest program length', `algorithmic randomness', and others. See the web page "http://www.cwi.nl/~paulv/kolmogorov.html" for more information. ------------------------------ From: bwhitehe@sparc2000.utsi.edu (Bruce Whitehead) Date: Fri, 21 Mar 1997 17:42:19 -0600 Subject: Short Course Announcement 4-DAY COURSE: GENETIC ALGORITHMS AND NEURAL NETWORKS May 13-16, 1997 University of Tennessee Space Institute OBJECTIVES: (i) To judge, for a given application, whether either a genetic algorithm or a neural network would be advisable. (ii) To choose a specific architecture and a specific adaptation/ learning procedure well-suited to that application. (iii) To knowledgeably apply the chosen technique, understanding its inner workings well enough to know whether it is doing what it should be, and if not, to experiment with different architectures and parameter settings intelligently, not blindly. INSTRUCTORS: David E. Goldberg, Professor of General Engineering, University of Illinois at Urbana-Champaign, author of "Genetic Algorithms in Search, Optimization, and Machine Learning" (Addison-Wesley, 1989). Bruce A. Whitehead, Associate Professor of Computer Science, University of Tennessee Space Institute. SCHEDULE: Tuesday, May 13, 1997 Fundamental Principles of Genetic Algorithms (Goldberg) Applicable Theory of Genetic Algorithms (Goldberg) Wednesday, May 14, 1997 Lab in Genetic Algorithms (Goldberg) Genetic Algorithm Architectures and Methods (Goldberg) Thursday, May 15, 1997 Fundamental Principles of Neural Networks (Whitehead) Lab in Neural Networks (Whitehead) Friday, May 16, 1997 Neural Network Architectures and Methods (Whitehead) Neural Network Application Software Design (Whitehead) FOR FURTHER INFORMATION A detailed course brochure is available at http://www.utsi.edu/ConEd/whitehe1.html A printed course brochure, enrollment/fee information, and travel/lodging information are available from Becky Stines, Short Course Office 615-393-7278 e-mail: bbright@utsi.edu Technical questions about the course content may be directed to Bruce Whitehead 615-393-7296 e-mail: bwhitehe@utsi.edu ------------------------------ From: Jaime Fernandez Date: Mon, 24 Mar 1997 19:43:46 -0500 Subject: New Home for The Genetic Programming Notebook The Genetic Programming Notebook has a new home. It is at: http://www.geneticprogramming.com/ The GP Notebook site contains information on the following categories: Genetic Programming GP Tutorial Software People Other Sites Research Groups Misc Bibliographies Papers Journals FAQ Calls for Papers Conferences Commercial Genetic Algorithms Genetic Algorithms Software People Other Sites Research Groups Misc Bibliographies Papers Journals FAQ Courses Parallel Repositories Tutorials Artificial Intelligence & Robotics Artificial Intelligence FAQs Newsgroups Machine Learning Artificial life Sites Fuzzy Logic Neural Nets Robots Financial Programming Jaime J. Fernandez Jr. | Email: jjf@jjf.com Metrica, Inc. | WWW: http://www.jjf.com Author of the GP Notebook: http://www.geneticprogramming.com/ And Castles of the World: http://www.castles.org/ ------------------------------ From: V Sundararajan Date: Fri, 21 Mar 1997 17:12:18 +0530 (IST) Subject: Help needed Dear Friends, I am working on structure optimisation of biomolecules using GA. I need the following reference. Could any body send the full paper. A paper by Lucasius and Kateyan in proceedings of ICGA '89. Secondly, I would like to know what is cyclic Genetic Algorithms. [ WMS: I would like to know what a cyclic GA is as well, so please reply to GA_List with that info... ] I would greatly appreciate your help in the above. Thanks in advance sundar V. Sundararajan, Applications group Centre for Development of Advanced Computing Pune University Campus, Pune 411 007 Phone: 352461/79/83/84 Ext 341/342 Direct 370098 Fax : +91 212 357551 e-mail: sundar@cdac.ernet.in ------------------------------ End of Genetic Algorithms Digest ******************************