Genetic Algorithms Digest Monday, 23 October 1989 Volume 3 : Issue 16 - Send submissions to GA-List@AIC.NRL.NAVY.MIL - Send administrative requests to GA-List-Request@AIC.NRL.NAVY.MIL Today's Topics: - New version of GENESIS available - GA conference? - NIPS Workshop on GA/ANN -------------------------------- Date: Wed, 18 Oct 89 12:45:23 PDT From: schraudo%cs@ucsd.edu (Nici Schraudolph) Subject: New version of GENESIS available Our research group here at UCSD has found John J. Grefenstette's GENESIS genetic algorithm simulator an invaluable tool for GA research, and the frequency with which we use it in different contexts has motivated us to put some effort into advancing the GENESIS source code itself. Starting from GENESIS 4.5 I have therefore developed three new versions of GENESIS over this summer. The first two of these (which fix a number of 4.5 bugs and improve the user interface, respectively) have been sent to John, who has kindly agreed to organize their distribution and integration into mainstream GENESIS. The third version includes more idiosyncratic improvements and facilities, and is available as "GENESIS 1.0ucsd" from us via anonymous ftp. Among a host of minor improvements 1.0ucsd offers the following new features: * simulations can be killed and restarted at will; * the setup program dynamically suggests default values for parameters; * additional termination criteria (Bias and Conv thresholds) are available; * evaluation functions may operate directly on the packed gene for speed; * almost any scalar C function can be used directly as evaluation function; * simulation queues may be executed in parallel on a network of hosts. Copies of the source code can be obtained as follows: $ mkdir GAucsd $ cd GAucsd $ ftp sdcsvax.UCSD.EDU Login: anonymous Password: ftp> cd pub/GA ftp> mget GENESIS.?.Z ftp> quit $ uncompress *.Z $ GENESIS.1 $ GENESIS.2 $ GENESIS.3 $ GENESIS.4 $ lpr UsersGuide $ view README WARNING: this is effectively a beta test version, and I can and will not give any guarantee of correctness. I will maintain a list of users for distributing bug fixes, updates, and new versions. To get added to that list, report bugs, or make suggestions send mail to nschraudolph@UCSD.EDU. GENESIS 1.0ucsd is an important tool for GA research in our group, and we expect it to continue evolving. For the near future we are planning the addition of ARGOT-style operation and fine-grain parallelism (using RPC to distribute evaluations). -- Nici Schraudolph Computer/Cognitive Science Research Group (CCSRG) nschraudolph@UCSD.EDU University of California, San Diego, C-014 ...!ucsd!nschraudolph San Diego, CA 92093 nschraudolph@UCSD.BITNET -------------------------------- Date: Tue, 17 Oct 89 10:02:33 -0500 From: Kadaba Nagesh Subject: GA conference? Could you please let me know, the significant GA conference scheduled in 1990 ? Thanks in advance. Nagesh [Moderator's note: There will not be a GA Conference in 1990, but there will be several workshops or conference session related to GAs. I will post all such announcements as they arrive. See below. -- JJG] -------------------------------- From: rudnick@cse.ogc.edu (Mike Rudnick) Date: Fri, 20 Oct 89 16:30:57 PDT Subject: NIPS Workshop on GA/ANN Dave Davis and I are organizing the NIPS (Neural Information Processing Systems conference) workshop described below. The workshops are informal and flexible, so the description presented below will undoubtedly change. ************************************************************************* 1989 NIPS WORKSHOP: NEURAL NETWORKS AND GENETIC ALGORITHMS Lawrence Davis Michael Rudnick BBN Laboratories Inc. Oregon Graduate Center 10 Moulton St. 19600 NW Von Neumann Drive Cambridge, Mass. 02138 Beaverton, OR 97006-1999 phone: (617) 873-3120 (503) 690-1121, X7390 e-mail: ddavis@BBN.COM e-mail: rudnick@cse.ogc.edu WORKSHOP DESCRIPTION Description: Genetic algorithms (GA) have many interesting relationships with neural networks (NN). Recently, a number of researchers have investigated some of these relationships. This workshop will be the first forum bringing those researchers together to discuss the current and future directions of their work. The workshop will last one day and will have three parts. First, a tutorial on GAs will be given, to ground those unfamiliar with the technol- ogy. Second, seven researchers will summarize their results. Finally there will be an open discussion on the topics raised in the workshop. We expect that anyone fami- liar with NN technology will be comfortable with the content and level of discussion in this workshop. The workshop will include a tutorial on GAs, presenta- tions by researchers active in GA/NN, and an open panel/audience discussion. It will bring together research- ers who are currently studying the relationships between NNs and GAs. Presentation of current results and discussion of future directions will be included. We anticipate attract- ing both interested onlookers and researchers active in this area. The workshop may well undergo change. NIPS meets Nov 27-30 in Denver with workshops Dec 1-2 at the Keystone ski resort. NIPS has a proceedings, the workshops don't. PROPOSED AGENDA Genetic Search Tutorial Tutorial on Genetic Algorithms for Neural Network Spe- cialists to be given by David Goldberg (U. of Alabama) or Lawrence Davis (Bolt Beranek and Newman). Davis gave the GA tutorial at the 1987 International Conference on GAs and is the editor of a book on GAs and simulated annealing; Gold- berg will give the tutorial at the next GA conference and is the author of a recent textbook on GAs. Both are experi- enced and effective presenters. Presentation of Research Probably six presentations on current research includ- ing the following. Most of these people have agreed to par- ticipate, but a few have not yet finalized their plans. We have sufficient speakers to fill in for any who are unable to come. Darrell Whitley (Colorado State University at Fort Collins) "Training Neural Networks with Genetic Algorithms" Rik Belew (University of California at San Diego) "Relationships between Classifier Systems and Neural Networks" Lawrence Davis (Bolt Beranek and Newman) "Hybridizing Neural Network, Genetic Algorithm, and Expert Heuristic Techniques" Bill Dress (Oak Ridge National Laboratory) "Genetic Optimization in Synthetic Organisms" Open Panel Discussion. The presenters above will discuss relevant issues with the audience, including directions for further research. Moderator will be Michael Rudnick (Oregon Graduate Center). This activity will probably expand to fill the time avail- able, if the level of activity at similar sessions in the past are any indication. -------------------------------- End of Genetic Algorithms Digest ********************************