Genetic Algorithms Digest Wednesday, February 26 1992 Volume 6 : Issue 7 - Send submissions to GA-List@AIC.NRL.NAVY.MIL - Send administrative requests to GA-List-Request@AIC.NRL.NAVY.MIL - anonymous ftp archive: FTP.AIC.NRL.NAVY.MIL (see v6n5 for details) Today's Topics: - SGA-C and SGA-Cube added to ga-list archive - ALIFE Course at Stanford - CFP: Comparative Approaches to Cognitive Science ********************************************************************** CALENDAR OF GA-RELATED ACTIVITIES: (with GA-List issue reference) Canadian AI Conference, Vancouver, May 11-15, 1992 COGANN, Combinations of GAs and NNs, @ IJCNN-92 (v5n31) Jun 6, 1992 ARTIFICIAL LIFE III, Santa Fe, NM Jun 15-19, 1992 10th National Conference on AI, San Jose, Jul 12-17, 1992 FOGA-92, Foundations of Genetic Algorithms, Colorado (v5n32) Jul 26-29, 1992 COG SCI 92, Cognitive Science Conference, Indiana, (v5n39) Jul 29-1, 1992 ECAI 92, 10th European Conference on AI (v5n13) Aug 3-7, 1992 Parallel Problem Solving from Nature, Brussels, (v5n29) Sep 28-30, 1992 SAB92, From Animals to Animats, Honolulu (v6n6) Dec 7-11, 1992 (Send announcements of other activities to GA-List@aic.nrl.navy.mil) ********************************************************************** ---------------------------------------------------------------------- From: rob@galab2.mh.ua.edu Date: Fri, 21 Feb 92 16:49:14 CST Subject: SGA-C and SGA-Cube added to ga-list archive [Ed's Note: These programs are available as compressed tar files via anonymous ftp from the ga-list archive at ftp.aic.nrl.navy.mil. They are in the directory pub/galist/source-code/ga-source. --Alan] I am pleased to announce that SGA-C and SGA-Cube have been added to the ga-list archive. README files for each of the progarms are included below: -----sga-c/README------- SGA-C: A C-language Implementation of a Simple Genetic Algorithm ARCHIVE FILENAME: pub/galist/source-code/ga-source/sga-c.tar.Z Robert E. Smith The University of Alabama David E. Goldberg The University of Illinois and Jeff A. Earickson Alabama Supercomputer Network TCGA Report No. 91002 SGA-C is a C-language translation and extension of the original Pascal SGA code presented in Goldberg's text (Goldberg, 1989). It has some additional features, but its operation is essentially the same as that of the original, Pascal version. A technical report (in PostScript file sga-c.ps) is included as a concise introduction to the SGA-C distribution. It is presented with the assumptions that the reader has a general understanding of Goldberg's original Pascal SGA code, and a good working knowledge of the C programming language. The report begins with an outline of the files included in the SGA-C distribution, and the routines they contain. The outline is followed by a discussion of significant features of SGA-C that differ from those of the Pascal version. The report concludes with a discussion of routines that must be altered to implement one's own application in SGA-C. The authors are interested in the comments, criticisms, and bug reports from SGA-C users, so that the code can be refined for easier use in subsequent versions. Please email your comments to @ua1ix.ua.edu:rob@galab2.mh.ua.edu, or write to TCGA: The Clearinghouse for Genetic Algorithms The University of Alabama Department of Engineering Mechanics P.O. Box 870278 Tuscaloosa, Alabama 35487 References: Goldberg, D.E. (1989). Genetic algorithms in search, optimization, and machine learning. Reading, MA: Addison-Wesley. ------sga-Cube/README------- SGA-Cube: A Simple Genetic Algorithm for nCUBE 2 Hypercube Parallel Computers ARCHIVE FILENAME: pub/galist/source-code/ga-source/sga-cube.tar.Z Jeff A. Earickson Alabama Supercomputer Network Robert E. Smith The University of Alabama and David E. Goldberg The University of Illinois TCGA Report No. 91005 SGA-Cube is a C-language translation of the original Pascal SGA code presented by Goldberg (1989) with modifications to allow execution on the nCUBE 2 Hypercube Parallel Computer. When run on the nCUBE 2, SGA-Cube takes advantage of the hypercube architecture, and is scalable to any hypercube dimension. The hypercube implementation is modular, so that the algorithm for exploiting parallel processors can be easily modified. In addition to its parallel capabilities, SGA-Cube can be compiled on various serial computers via compile-time options. In fact, when compiled on a serial computer, SGA-Cube is essentially identical to SGA-C (Smith, Goldberg, & Earickson, 1991). SGA-Cube has been nominally tested on a Sun 470 workstation, a Vax Ultrix system, a Cray X-MP/24 running UNICOS 5.1, and the nCUBE 2. A technical report (in PostScript file sga-cube.ps) is included as a concise introduction to the SGA-Cube distribution. It is presented with the assumptions that the reader has a general understanding of Goldberg's original Pascal SGA code, and a good working knowledge of the C programming language. The report begins with an outline of the files included in the SGA-Cube distribution, and the routines they contain. The outline is followed by a discussion of the significant features of SGA-Cube. The report concludes with a discussion of routines that must be altered to implement one's own application in SGA-Cube. The authors are interested in the comments, criticisms, and bug reports from SGA-Cube users, so that the code can be refined for easier use in subsequent versions. Please email your comments to @ua1ix.ua.edu:rob@galab2.mh.ua.edu, or write to TCGA: The Clearinghouse for Genetic Algorithms The University of Alabama Department of Engineering Mechanics P.O. Box 870278 Tuscaloosa, Alabama 35487 Goldberg, D.E. (1989). Genetic algorithms in search, optimization, and machine learning. Reading, MA: Addison-Wesley. Smith, R.E., Goldberg, D. E., & Earickson, J. (1991). SGA-C: A C-language implementation of a simple genetic algorithm (TCGA Report No. 91002). Tuscaloosa: The University of Alabama, The Clearinghouse for Genetic Algorithms. Robert Elliott Smith Department of Engineering of Mechanics Room 210 Hardaway Hall The University of Alabama Box 870278 Tuscaloosa, Alabama 35487 <> @ua1ix.ua.edu:rob@galab2.mh.ua.edu <> (205) 348-1618 <> (205) 348-6419 ------------------------------ From: John Koza Date: Fri, 21 Feb 92 10:48:26 PST Subject: ALIFE Course at Stanford You may be interested in the following.. ALIFE COURSE AT STANFORD Starting in Fall 1992, a new course in the Computer Science Department will be offered. The Course description follows: Existing carbon-based lifeforms exploit available energy (primarily from the sun) to organize available matter in order to survive, reproduce, and evolve, whereas computational forms of artificial life exploit computer time to organize computer memory to the same effect. The course extrapolates the computational characteristics of existing lifeforms to life as it might be by presenting artificial life from the perspective of the major tools and the major issues of the field. Tools include self-reproducing cellular automata, dynamical systems, genetic algorithms, genetic programming, neural nets, genomic processes, and nanotechnology. Issues include spontaneous emergence of self-replicating and self-improving computer programs; self-replicating matter; programmable matter; algorithmic chemistry; evolution; learning; and emergent computation. 3 units, Fall (Koza), MW 1:15-2:30 For additional information, contact John Koza Computer Science Department Margaret Jacks Hall Stanford University Stanford, California 94305 ------------------------------ From: Herbert Roitblat Date: Tue, 18 Feb 92 15:30:51 HST Subject: CFP: Comparative Approaches to Cognitive Science Call for Participation Comparative Approaches to Cognitive Science (CACS92): An International Summer School CACS92 is an international summer school to be held in Aix en Provence, France, July 6-17, 1992 on comparative approaches to cognitive science. This school will bring together leading investigators in animal and human cognition, artificial intelligence, and robotics to discuss, compare, and share the concepts, problems, and techniques that characterize their fields of investigation. It will also offer numerous opportunities for collaboration. Its main goals are to discuss the role that investigations of animals and machines can play in the development of cognitive science generally, and to provide the intellectual and methodological tools necessary to the advancement of such developments. A major focus in cognitive science has been on modeling the performance of tasks that are characteristic of human intelligence, such as planning, problem solving, scientific creativity, and the like. Several investigators have recently suggested the possibility of a complementary comparative approach to cognitive science. Rather than modeling toy problems from the larger domain of human expert behavior, this approach advocates the modeling of whole, albeit simple, organisms in a real environment, performing real biological tasks (surviving, exploring, mating, feeding, escaping predators, etc.). The goal of the approach is to develop coherent incremental models out of functionally complete components. Achieving this goal requires that we investigate animal performance and the mechanisms they use as the basis for our growing models. It also requires extensive collaborations among ethologists, psychologists, computer scientists, engineers, and cognitive scientists because no one of these fields, by itself, has the tools to thoroughly understand the mechanisms of such complex processes. The purpose of this summer school is to review the state of the art in this interdisciplinary approach and to share the tools and perspectives it requires. The summer school will be held at the Ecole d'Art d'Aix en Provence, France, from July 6-17, 1992. Aix is in a beautiful part of France known as a favorite location for many of the Impressionist painters. The summer school will consist of morning lectures followed by afternoon discussions. English will be the official language. We have asked the instructors to prepare presentations that are accessible as tutorials to the students and are broader than normal, that describe not only the investigator's own interests, but also review the state of the art, and describe the theoretical and empirical tools that are employed. We have also asked them to draw explicit conclusions concerning how the work they describe impacts on cognitive science more generally. Presentations will draw specific conclusions about the role that cognition plays in solving behavioral problems and identify the kinds of organisms and environments in which such mechanisms may be useful. During the summer school, the Ecole d'Art d'Aix will simultaneously organize a series of artistic activities and demonstrations including conferences, workshops, and shows, for which artists of many nationalities have been invited to contribute works along the same themes as those of the planned summer school (artificial life, behavioral organization, networks, interconnectedness, robots, animal behavior, etc.). Many opportunities for interaction among the scientific and artistic participants will be available. This promises to be an excellent and influential summer school. In addition to the invited speakers, a limited number of participants/students can be accommodated. Advanced graduate students, young researchers, new PhDs, and post-docs are particularly welcome. Participants are invited to submit abstracts for poster presentations during the summer school. The costs to participants have not yet been determined. We expect that the registration fee for the summer school will be approximately FF4,500, which would cover summer school registration, room (in student housing at the University of Aix) and board. We expect some scholarship support to be available to help offset these costs. Prospective participants are urged to indicate their interest as soon as possible because space is limited. Participants should submit the following: A letter describing their interest in the subject matter of the conference and a curriculum vitae. Include a full mailing address, electronic mail address, and FAX number. If scholarship support is desired then a letter of recommendation from the participant's advisor or department chair is also required. Please indicate the amount of scholarship support desired. Those desiring to present posters should submit a one-page abstract. Centered at the top of the page should be the complete title, author name(s) with the presenting author underlined, affiliation(s), and complete mailing address. This is followed by a blank space and the text of the abstract. One copy of all material should be sent to each of the summer school organizers: Herbert ROITBLAT Jean-Arcady MEYER Department of Psychology Groupe de Bioinformatique University of Hawaii at Manoa URA686.Ecole Normale 2430 Campus Road Superieure Honolulu, HI 96822 46 rue d'Ulm USA 75230 Paris Cedex 05 email: roitblat@uhunix.bitnet, France roitblat@uhunix.uhcc.hawaii. e-mail: meyer@frulm63.bitnet edu Organizing Committee and local arrangements CYPRES Groupe de BioInformatiq Ecole d'Art Ecole Normale Superieure Rue Emile Tavan 46 rue d'Ulm 13100 Aix-en-Provence Paris Cedex 05 Tel (33) 42 27 57 35 Tel (33) 44 32 36 23 FAX (33) 42 27 63 99 FAX (33) 44 32 39 01 Tentative Program Comparative Approaches to Cognitive Science (CACS92) * Indicates participation to be confirmed Introduction Jean-Pierre Changeux (France) From non-human to human cognition: challenge and prospects Herbert Roitblat (USA) Comparative approach as a tool in cognitive science Jean-Arcady Meyer (France) Computational approaches to cognition Marc Bekoff (USA) Cognitive ethology, common sense, and the explanation of animal behavior Perception and action Tom Bourbon (USA) Perceptual control theory: Modelling conflict, cooperation and control George Butterworth (UK) Factors in visual attention eliciting manual pointing in human infancy Steven Whitehead (USA) Towards a computational theory of perception, action and learning Concept formation Roger Thompson (USA) Natural concepts and self-concept in animals Lorenzo Von Fersen (Germany) Abstract and natural concept formation in animals Keith Holyoak (USA) Natural and artificial induction Internal world models Julie Neiworth (USA) Internal models of space, time, and movement in animals Catherine Thinus-Blanc (France) Spatial information processing in animals Bartlett Mel (USA) Mechanisms and applications of associative learning in biological sensory and motor systems Motivation and emotion Frederick Toates (UK) Animal motivation and cognition Janet Halperin (Canada) Cognition and emotion in animals and machines Niko Frijda (Netherlands) Emotions in robots Intentionality Daniel Dennett (USA) Animals and human beings as intentional systems: The fundamental difference David McFarland(UK) Goals, no-goals and own-goals Peter Kugler (USA) Informational fields and intentional action Colin Allen (USA) Intentionality: natural and artificial Language, Communication and Cooperative Behavior * Peter Marler (USA) Communication in animals Sue Savage-Rumbaugh (USA) Cooperative communication by pygmy chimpanzees * Giulio Sandini (Italy) Cellular robotic systems Learning Randy Gallistel (USA) Time representation and conditioning in animals Jean Delacour (France) The memory system of the mammalian brain Richard Sutton (USA) Learning and planning Leslie Kaelbling (USA) Reinforcement learning in robots Evolution * David Premack (USA) Evolution of cognition Michael Dyer (USA) Symbol Grounding and Evolution of Primitive Communication Rik Belew (USA) Interacting models of evolution, ontogeny and learning Conclusions John Anderson (USA) Margaret Boden (UK): Creativity in Humans and Machines Rodney Brooks (USA) ------------------------------ End of Genetic Algorithms Digest ******************************