Genetic Algorithms Digest Thurs, Jan 7, 1999 Volume 13 : Issue 1 - 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: - For GA Digest discussion - GA and Games - Help for classification of problem -thesis - CFP: Special issue on Multi-Criterion Optimization - CFP: IJCAI'99 Workshop on Sequence Learning - 2nd Call for Papers: Special issue on advances in GAs - CFP: Soft Computing Applied to Software Engineering - Recent Advances in Soft Computing'99 reminder ---------------------------------------------------------------------- CALENDAR OF GA-RELATED ACTIVITIES: (with GA-List issue reference) Intl Conf on Evol Computation in Engin, Chennai, India (v12n1) Jan 6-9, 99 CF99 Computational Finance, New York, NY (v12n10) Jan 6-8, 99 CIMCA99 Comp Intell for Mod Cont and Aut, Vienna, Aust (v12n10) Feb 17-19, 99 SAC99 14th Annual ACM Symposium on Applied Computing (v12n7) Feb 28-Mar 2, 99 CIMAF99 Symposium on Artificial Intelligence (v12n5) Mar 22-26, 99 SPIE Applications and Sci of Comp Intell, Orlando, FL (v12n10) Apr 5-9, 99 AISB Symp. on Creative Evol. Systems, Edinburgh, UK (v12n19) Apr 6-9, 99 ICANNGA99 Int Conf on NNs and GAs, Portoroz, Slovenia (v12n21) Apr 6-9, 99 SCASE99 Soft Computing Applied to SW Engr, Ireland (v13n1) Apr 12-14, 99 EuroGP99 2nd Euro Workshop on GP, Goteborg, Sweden (v12n20) May 26-27, 99 EvoIASP99 1st Euro WS on EC in Image Anal & Sig Proc (v12n18) May 28, 99 EuroEctel99 1st Euro Workshop on EC in Telecommunicati (v12n16) May 29, 99 SOCO99 Soft Computing, Genova, Italy (v12n8) Jun 1-4, 99 ISAMA99 Int Soc for Arts, Math and Arch, Spain (v12n21) Jun 7-11, 99 MENDEL99 5th Int Mendel Conf on Soft Comp, Czech Rep (v12n23) Jun 9-12, 99 TAINN99 8th Turkish Symposium on AI and Neural Nets (v12n17) Jun 23-25, 99 CEF99 EC in Economics and Finance, Chestnut Hill, MA (v12n21) Jun 24-26, 99 ICML99 16th Int Conf on Mach Learning, Bled, Slovenia (v12n21) Jun 27-30, 99 Recent Advances in Soft Computing99, Leicester, UK (v12n20) Jul 1-2, 99 CEC99 Congress on Evol Computation, Washington, DC (v12n9) Jul 6-9, 99 GECCO99 Genetic & Evol Computation Conf, Orlando, FL (v12n8) Jul 13-17, 99 AAAI99 16th National Conference on AI, Orlando, FL (v12n21) Jul 18-22, 99 EH99 1st NASA/DOD WS on Evol Hardware, Pasadena, CA (v12n23) Jul 19-21, 99 IJCAI99 WS on Neur, Symb, & Reinfcmt Meth for Sequ Lear (v13n1) Aug 1, 99 IJCAI99 WS on Agents Learning About, From, and With Ot (v12n22) Aug 2, 99 ECAL99 5th Euro Conf on Artificial Life, Lausanne, Swi (v12n20) Sep 13-17, 99 RSFDGrC99 7th Int WS Rough Sets, Fuzzy Sets, Data Min (v12n22) Nov 9-11, 99 IAT99 Intelligent Agent Technology, Hong Kong (v12n21) Dec 15-17, 99 Send announcements of other activities to GA-List@aic.nrl.navy.mil. ------------------------------ Date: Tue, 22 Dec 1998 05:01:30 PST From: "sivakumar palaniappan" Subject: For GA Digest discussion Dear Sir, I am a research scholar in Building Technology and Construction Management Division at IIT Madras India. I am doing research work in the area "GA for path planning of cooperative manipulators". I want discuss with researchers working in the above area. I also expect literature related to this area. If you have published any papers related to this area please send to me. My mail address: plsiva@hotmail.com plsiva@bantha.civil.iitm.ernet.in PL.Sivakumar M.S. Research Scholar BT&CM Division Department of Civil Engineering Indian Institute of Technology Madras Chennai - 600036 INDIA ------------------------------ Date: Tue, 22 Dec 1998 20:56:49 +0100 (MET) From: Pier Luca Lanzi Subject: GA and Games Hello everybody, I am looking for some reference on the use of GAs to game-playing. In particular I am not looking for co-evolution but algorithms which optimize the function for deciding the best move in an AND-OR tree. Thank you. Pier Luca Lanzi ------------------------------ Date: Wed, 23 Dec 1998 10:58:37 +0200 From: Tanju Ataylar Subject: Help for classification of problem -thesis i have reached your address from web site that consist of some discussion on GA, GGA and optimization problems. i have seen some message which are really significant and usefull for related topics. i am in trouble with classify or define the following problem which i am intresting in. I have one source metal sheet and several rectangular shape will be cut from source sheet. the problem is the optimization of rectangular's location on the source. some programers call nesting problem for this combinatorial prob. just i would like to know: which algorithms are suitable for this problem ? what is the name of this problem ? and where is stated on the optimization algorithms (tree) ? is it possible to point me any similar study? thanks and i am looking forward to hearing you answer. please reply to : karina@kosgeb.tekmer.gov.tr Tanju Ataylar ------------------------------ Date: Wed, 23 Dec 1998 10:30:59 +0100 From: Kalyanmoy Deb Subject: CFP: Special issue on Multi-Criterion Optimization Interested persons are encouraged to send papers for the following special issue. Please note that the deadline for receiving papers is 15 February 1998. Kalyanmoy Deb CALL FOR PAPERS A Special Issue on `Multi-Criterion Optimization' =========================== Evolutionary Computation Journal, MIT Press Guest Editors: Kalyanmoy Deb and Jeffrey Horn Submission Deadline: 15 February, 1999 The principle of multi-criterion optimization is different from that of single objective optimization. The focus in multi-criterion optimization is on finding a number of Pareto-optimal solutions (i.e., alternative compromises among conflicting objectives), rather than finding a single, globally optimal solution. Many practical search and optimization problems are better posed as multi-criterion optimization problems and are, therefore, important to study. Classical search and optimization methods convert multiple objective functions into one scalar function, and can at best find a single Pareto-optimal solution at a time. In order to achieve multiple tradeoff solutions, these methods are applied repeatedly, each time varying the user-defined parameters for aggregating the multiple objectives. In contrast, evolutionary methods can find multiple Pareto-optimal solutions simultaneously, using their population-based searches. Because of this parallel searching and freedom from user-defined parameters, evolutionary approaches have a unique advantage over classical methods in solving multi-criterion optimization problems. In this special issue we plan to include various implementations of evolutionary approaches for multi-criterion optimization and their applications to real-world problems. Particularly, the following broad topics will be considered: 1. Theoretical issues (e.g., convergence to the Pareto-optimal set, etc.) 2. Implementation of multi-criterion evolutionary methods and proof-of-principle results 3. Comparison of different evolutionary methods (and classical methods) 4. Real-world applications 5. Test problem sets for multi-criterion optimization 6. Integration of evolutionary approaches with the multi-criterion decision process (e.g., iterative use of evolutionary search and human choice, etc.) We are particularly concerned with pragmatic issues, such as sensitivity of the solutions or the scalability of the approaches (e.g., to large numbers of conflicting objectives.) Interested persons are invited to submit original, full-length papers before 15th February 1999. The style of the paper must be according to requirements of the Evolutionary Computation Journal (8,000 to 12,000 words in length, single-sided and double-spaced). Accepted paper must be submitted in Latex. References should be in APA format both in the text and in the reference list. The expected date of publication is early 2000. Please send five hard-copies or a postscript file of your paper before 15 February 1999 to one of the following addresses: Kalyanmoy Deb Jeffrey Horn Systems Analysis Group Department of Math. and Computer Sc. Department of Computer Science Northern Michigan University University of Dortmund 1401 Presque Isle Avenue Joseph-von-Fraunhofer-Str. 20 Marquette, MI 49855-5340 44221 Dortmund, Germany USA deb@ls11.informatik.uni-dortmund.de jhorn@nmu.edu Phone: +49 231 9700974 Phone: 906/227-1607 We also plan to publish short descriptions of any public domain software implementing multi-criterion optimization using EC methods. Interested persons may contact one of the guest editors for details. Any queries about the special issue can be forwarded to any of the guest editors. We are looking forward to having your contribution. Kalyanmoy Deb (deb@ls11.informatik.uni-dortmund.de) Jeffrey Horn (jhorn@nmu.edu) Guest Editors, Special issue on `Multi-Criterion Optimization' ------------------------------ Date: Mon, 28 Dec 1998 14:22:15 -0500 From: Ron Sun Subject: CFP: IJCAI'99 Workshop on Sequence Learning CALL FOR PAPERS IJCAI'99 Workshop on NEURAL, SYMBOLIC, AND REINFORCEMENT METHODS FOR SEQUENCE LEARNING to be held during IJCAI'99 Stockholm, Sweden, 31 July - 6 August, 1999 http://www.cs.cmu.edu/~ijcai99 Sequence learning is an important component of learning in many task domains: inference, planning, reasoning, robotics, natural language processing, speech recognition, control, time series prediction, financial engineering, DNA sequencing, etc. There are many different approaches towards sequence learning, resulting from different perspectives taken in different task domains. These approaches deal with somewhat differently formulated sequential learning problems (for example, some with actions and some without). Sequence learning is a difficult task, and more powerful algorithms are needed in all of these domains. The right approach is to better understand the state of the art in different disciplines related to this topic first. Therefore, there seems to be a need to compare, contrast, and combine different techniques, approaches, and paradigms, to develop more powerful algorithms. These techniques and algorithms include recurrent neural networks, hidden Markov models, dynamic programming (reinforcement learning), graph theoretical models, evolutionary computational models, AI planning models, rule-based models, etc. We need a gathering that includes researchers from all of these orientations and disciplines, beyond narrowly focused topics such as reinforcement learning or neural networks for sequential processing. The following questions and issues will be addressed: 1. underlying similarity and difference of different models 1.1 problem formulation (ontological issues) 1.2 mathematical comparisons 1.3 task appropriateness 1.4 performance analysis and bounds 2. new and old model capabilities and limitations 2.1 theory 2.2 implementation 2.3 performance 2.4 empirical comparisons in various domains 3. hybrid models: approaches, theories and applications 3.1 foundations for synthesis or hybridization 3.2 necessity, advantages, problems, and issues 4. successful sequence learning applications and future extensions 4.1 examples of successful applications 4.2 generalization and transfer of successful applications 4.2 what is needed for enhancing performance 1. We welcome submissions from all disciplines related to sequence learning, including: AI researchers, cognitive scientists, control engineers, computer scientists, neural network researchers, and mathematicians, in the areas of recurrent neural networks, hidden Markov models, dynamic programming (reinforcement learning), graph theoretical models, evolutionary computational models, AI planning models, rule-based models, etc. 2. To present a talk at the workshop, please submit (to one of the workshop chairs) a short paper (between 2 and 7 pages), in the IJCAI paper format. It must describe work and stating opinions relative to the above issues. 3. To participate in the workshop, submit a one-page description of interest to one of the workshop chairs. 4. All submission should be through EMAIL, with plain Postscript files. 5. time table: February 15, 1999 Deadline for paper submission March 15, 1999 Notification of acceptance April 1, 1999 Camera ready copy Dr. C. Lee Giles (co-chair) NEC Research Institute 4 Independence Way Princeton, NJ 08540, USA Phone: 609-951-2642 Email: giles@research.nj.nec.com http://www.neci.nj.nec.com/homepages/giles.html Professor Ron Sun (co-chair) Department of Computer Science The University of Alabama Tuscaloosa, AL 35487 Phone: 609-951-2781 Email: rsun@cs.ua.edu http://cs.ua.edu/~rsun/ [ASW: For additional information, please see the workshop web page at http://www.cs.cmu.edu/~ijcai99/workshop-27.html or the IJCAI workshops page at http://www.cs.cmu.edu/~ijcai99 .] ------------------------------ Date: Wed, 6 Jan 1999 09:37:29 -0500 (EST) From: Lashon Booker Subject: 2nd Call for Papers: Special issue on advances in GAs CALL FOR PAPERS Evolutionary Computation Journal Special Issue on Advances in Genetic Algorithms: Research Trends and Perspectives Submission deadline: March 1, 1999 Guest Editors: Lashon Booker and Rick Riolo More than 20 years ago, John Holland published the book "Adaptation in Natural and Artificial Systems" describing a general framework for understanding the mechanisms responsible for adaptive change in a variety of systems over a broad range of timescales. Initially, appreciation of the intellectual scope and significance of this monograph was limited to Holland's students and colleagues. Over the years, as Holland continued to develop his ideas and published other books and papers building on his basic framework, the influence of Holland's ideas has steadily grown. Today, John Holland is regarded in many circles as a visionary whose insights address critical issues relevant to scientific inquiries in fields as diverse as economics, immunology, cognitive science, and ecology. His research has also provided much of the intellectual foundation for the new science of complexity. Holland's insights have provided the starting point for many computational models of adaptation, including genetic algorithms, classifier systems, genetic programming, and Echo. His ideas have also influenced work in other research paradigms in evolutionary computation and in machine learning. As we approach the 25 year anniversary of the publication of Holland's landmark book, now is an opportune time to assess the impact of Holland's work on our understanding of adaptive systems and evolutionary computation. What are the common themes that have emerged from the diverse research efforts stemming from Holland's ideas? How close are we to a deeper theoretical understanding of the phenomena Holland has characterized so clearly and persuasively? What research remains to be done? This special issue will focus on the impact and significance of the themes underlying John Holland's research, characterizing what has been accomplished, open research issues, and promising lines of inquiry. Topics of interest include, but are not limited to, the following: - Characterizations of Holland's vision of adaptive systems and the implications of that vision - Discussions of open issues, trends, or unsolved problems in genetic algorithms, Echo, etc. - Descriptions of important developments or promising research directions related to Holland's work - Research that illustrates the themes of Holland's work in new and interesting ways - Comparisons of Holland's ideas with views from other paradigms or related disciplines Authors intending to submit a manuscript should contact one of the guest editors as soon as possible to discuss the suitability of their ideas for this special issue. Electronic submission (postscript or pdf) is preferred. For hard copy submission, please send five (5) copies of the full paper to one of the guest editors. Manuscripts should be single sided and double spaced. The first page should include the title, abstract, key words, and author information (name, affiliation, mail address, telephone number, and electronic mail address). The text of the paper should begin on the second page and continue on consecutively numbered pages. Lashon Booker Rick Riolo The MITRE Corporation Program for Study of Complex Systems (PSCS) 1820 Dolley Madison Blvd 4477 Randall Lab McLean, VA 22102-3481 University of Michigan E-mail: booker@mitre.org Ann Arbor MI 48109-1120 Phone: (703) 883-7609 E-mail: rlriolo@umich.edu Fax: (703) 883-6435 Phone: (734) 763-3323 Fax: (734) 763-9267 ------------------------------ Date: Wed, 6 Jan 1999 16:11:18 +0000 (GMT) From: Conor Ryan Subject: CFP: Soft Computing Applied to Software Engineering CALL FOR PAPERS Soft Computing Applied to Software Engineering Limerick, Ireland, April 12 - 14, 1999 http://scare.csis.ul.ie/scase99 The challenges of Software Engineering are still with us, despite more than twenty years of research effort. Soft Computing in its various forms offers promising methods for a wide variety of areas, from classical optimisation to poorly defined design problems. This workshop aims to explore the application of Soft Computing techniques to difficult problems in Software Engineering. Topics include, but are not limited to, the application of Soft Computing methods such as: evolutionary algorithms fuzzy logic neural networks simulated annealing and to Software Engineering problems such as: metrics driven design re-modularisation parallelisation software visualisation and documentation software cost estimation characterisation of design patterns and architectures clone detection Intending participants are requested to submit either a research paper (up to 5000 words), a position paper (about 1000 words), or a brief description of a system demonstration (about 1000 words plus sample screenshots). Submissions should be made in postscript by email to scase99@ul.ie, by January 30, 1999. Authors will be notified of acceptance by February 28, 1999, and camera-ready papers for the proceedings are due by March 12, 1999. A small amount of support may be available for student participants. Attendance will be limited to at most 30 participants, in order to encourage the free flow of ideas. There is no registration fee, but early registration is recommended to ensure a place. The proceedings (including all contributions) will be published by the University of Limerick, and a special issue of a journal is planned. The workshop will be held at the University of Limerick. Organising committee: Jim Buckley, Tony Cahill, JJ Collins, Peter Eades, Patrick Healy, Laur Ivan, Conor Ryan, and Alan Sheahan. [ASW: For additional information, please see the workshop web page at http://scare.csis.ul.ie/scase99 .] ------------------------------ Date: Wed, 6 Jan 1999 16:16:14 +0000 (GMT) From: Bob John Subject: Recent Advances in Soft Computing'99 reminder *** REMINDER AND FINAL CALL FOR PAPERS *** ** SHORT ABSTRACTS DUE JANUARY 31ST ** RECENT ADVANCES IN SOFT COMPUTING'99 De Montfort University Leicester United Kingdom July 1st and 2nd 1999 This international two day workshop brings together researchers in the field of "soft computing" - neural networks, fuzzy logic and genetic algorithms. This event follows on from a successful event in 1998. The nature of soft computing is that there is a wide diversity of techniques and applications and it is hoped that this diversity will be exhibited in the papers accepted. Topics of interest include: - Fuzzy Logic - Hybrid Systems - Genetic Algorithms - Fuzzy Control - Neuro-Fuzzy Systems - Fuzzy Decision Making - Genetic Programming Application areas may include, but are not limited to: - Engineering - Financial Services - Design - Data Analysis - Signal Processing - Robotics - Manufacturing - Architecture - Databases - Medicine - Information Systems Submission of abstract 31st January 1999 Notification of acceptance 15th March 1999 Camera-Ready versions 23rd April 1999 Authors are invited to submit two copies of an extended abstract of 1500-2000 words to: Bob John Centre for Computational Intelligence Faculty of Computing Sciences and Engineering De Montfort University Leicester LE1 9BH, UK Email: rij@dmu.ac.uk WWW: http://www.cms.dmu.ac.uk/~rij/rasc99cfp.html [ASW: For additional information, please see the workshop web page at http://www.cms.dmu.ac.uk/~rij/rasc99cfp.html .] ------------------------------ End of Genetic Algorithms Digest ******************************