This is a bibliography of work relating artificial neural networks (ANNs) and genetic search. The Unix bib format is used throughout. It is organized/oriented for someone familiar with the ANN literature but less familiar with the genetic search literature. It includes some artificial life references. I am a phd candidate in computer science at Oregon Graduate Institute interested in tackling ANN architectural design using genetic search. My particular orientation is to view minimizing interconnections as a central issue, partly motivated by VLSI implementation issues. I have started a mailing list for those interested in using genetic search and ANNs together in various ways. Mail to Neuro-evolution-request@cse.ogi.edu for administrivia, answers to questions, or to have your name added to the list. Much thanks to the people who helped provide this bibliography by providing references. Corrections and additional references are welcome. Mike Rudnick CSnet: rudnick@cse.ogi.edu Computer Science & Eng. Dept. ARPAnet: rudnick%cse.ogi.edu@relay.cs.net Oregon Graduate Institute BITNET: rudnick%cse.ogi.edu@relay.cs.net 19600 N.W. von Neumann Dr. UUCP: {tektronix,verdix}!ogicse!rudnick Beaverton, OR. 97006-1999 (503) 690-1121 X7390 ****************************************************************************** %A David Ackley %T A Connectionist Machine for Genetic Hillclimbing %D 1987 %I Kluwer Academic Publishers %X Ackley's phd thesis. Compartive study between Ackley's fairly baroque "connectionist" learning architecture and several alternatives which include genetic search and random. %A David H. Ackley %A Michael L. Littman %T Learning from natural selection in an artificial environment %A J. M. Baldwin %T A new factor in evolution %J American Naturalist %D 1896 %V 30 %P 441-451 %A Richard K. Belew %T When both individuals and populations search: Adding simple learning to the Genetic Algorithm %D 1989 %A Richard K. Belew %A Michael Gherrity %T Back propagation for the Classifier System %J Proceedings of the Third Intl. Conf. on Genetic Algorithms %I Morgan Kaufmann %D 1989 %A R. K. Belew %A M. Gherrity %T Connectionism and the Classifier System %C La Jolla, CA %D 1989 %I Univ. Calif. San Diego %R CSE Department %A R. K. Belew %T Evolution, learning and culture: Computational metaphors for adaptive search %D 1989 %I UC San Diego %R CSE Technical Reoprt #CS89-156 %A T. J. A. Bennett %T Self-Organizing Systems and Transformational-Generative (TG) Grammar %D 1988 %J Cybernetics and Systems: An International Journal %P 61-81 %V 19 %A Aviv Bergman %A Michel Kerszberg %T Breeding Intelligent Automata %J Proceeding of the IEEE First Annual Conference on Neural Networks %C San Diego %D 1987 %A Lashon B. Booker %T Using Classifier Systems to Implement Distributed Representations %J IJCNN-90-WASH-DC %D 1990 %E Maureen Caudill %V 1 %P 39-42 %A John L. Casti %T Alternate Realities: Mathematical Models of Nature and Man %D 1989 %I Wiley Interscience %X A far ranging mathematical overview of things including evolution. %A Thomas P. Caudell %A Charles P. Dolan %T Parametric Connectivity: Training of Constrained Networks using Genetic Algorithms %C Los Alamos, NM %D 1990 %J Proceedings of the Emergent Computation 1989 Conference %X Uses constrained (linked) weights (ie, spread networks) trained via genetic search. %E Stephanie Forest %A Thomas P. Caudell %A Charles P. Dolan %T Parametric Connectivity: Training of Constrained Networks using Genetic Algorithms %J Proceedings of the Third International Conference on Genetic Algorithms %E J. David Schaffer %D 1989 %I Morgan Kaufmann %P 370-374 %X Uses constrained (linked) weights trained via genetic search. %A M. Compiani %A D. Montanari %A R. Serra %A G. Valastro %T Classifier Systems and Neural Networks %E E. Caianiello %B Parallel Architectures and Neural Networks %P 105 - 118 %I World Scientific Publishers %C Singapore %D 1988 %A Lawrence Davis %T Mapping Neural Networks into Classifier Systems %J Proceedings of the Third International Conference on Genetic Algorithms %E J. David Schaffer %D 1989 %I Morgan Kaufmann %P 375-378 %A A. K. Dewdney %T Computer Recreations: Exploring the field of genetic algorithms in a primordial computer sea full of flibs %D November 1985 %J Scientific American %P 21-32 %A Charles P. Dolan %A Michael G. Dyer %T Towards the Evolution of Symbols %J Genetic Algorithms and Their Applications: Proceeding of the Second International Conference on Genetic Algorithms %D 1987 %I Morgan Kaufmann %E John J. Grefenstette %A W. B. Dress %A J. R. Knisley %T A Darwinian Approach to Artificial Neural Systems %J 1987 IEEE Conference on Systems, Man, and Cybernetics %D 1987 %A W. B. Dress %T Darwinian Optimization of Synthetic Neural Systems %J Proceeding of the IEEE First Annual International Conference on Neural Networks %D 1987 %A W. B. Dress %T Genetic Optimization in Synthetic Systems %D 1989 %A W. B. Dress %T Electronic Life and Synthetic Intelligent Systems %I Instrumentation and Controls Division, Oak Ridge Natuional Laboratory %D 1990 %A W. B. Dress %T In-Silico Gene Expression: A Specific Example and Possible Generalizations %J Proceedings of Emergence and Evolution of Life-Forms %D 1990 %A A. J. Fenanzo,\ Jr. %T Darwinian Evolution as a Paradigm for AI Research %I Harding Lawson Associates %J SIGART Newsletter %D July 1986 %N 97 %P 22-23 %A Hugo De Garis %T Genetic Programming: Building Nanobrains with GEnetically Programmed Neural Network Modules. %I CADEPS AI Research Unit, Universitye Libre de Bruxelles, CP 194/7, B-1050 Brussels, Belgium %D 1990 %A A. Gierer %T Spatial organization and genetic information in brain development %D 1988 %J Biological Cybernetics %P 13-21 %V 59 %A Jean-Charles Gille %A Stefan Wegrzyn %A Pierre Vidal %T On some models for developmental systems, Part IX: Generalized generating word and genetic code %D 1988 %J Int. J. Systems Sci %N 6 %P 845-855 %V 19 %A Steven Alex Harp %A Tariq Samad %A Aloke Guha %T Towards the Genetic Synthesis of Neural Networks %J Proceedings of the Third International Conference on Genetic Algorithms %E J. David Schaffer %D 1989 %I Morgan Kaufmann %P 360-369 %X Using GA for design of backprop nets. %A Steven Alex Harp %A Tariq Samad %A Aloke Guha %T Genetic Synthesis of Neural Networks %R Technical Report CSDD-89-I4852-2 %D 1989 %I Honeywell %X Using GA for design of backprop nets. %A Steven Alex Harp %A Tariq Samad %A Aloke Guha %T Designing Application-Specific Neural Networks Using the Genetic Algorithm %J NIPS-89 Proceedings %D 1990 %A H. M. Hastings %A S. Waner %T Principles of evolutionary learning: design for a stochastic neural network %D 1984 %Z this ref from SIGART Newsletter, Jan 1986, Number 95, p 31 %A Harold M. Hastings %A Stefan Waner %T Biologically Motivated Machine Intelligence %D 1986 %J SIGART Newsletter %N 95 %P 29-31 %A Geoffrey E. Hinton %A Steven J. Nolan %T How Learning Can Guide Evolution %I Carnegie Mellon University %D 1986 %R CMU-CS-86-128 %A R. Colin Johnson %T Avoiding the AI Trap: Synthetic Intelligence %D January 4, 1988 %J Electronic Engineering Times %A Michel Kerszberg %T Genetics and epigenetics of neural wiring %J Snowbird Abstracts %D 1988 %A Michel Kerszberg %T Genetic \^ and \^ Epigenetic \^ Factors \^ in \^ Neural \^ Circuit \^ Wiring %D 1988 %I Institut fu\*:r Festkorperforschung der %Z address: Kernforschungsanlage Julich, D-5170 Jurlich, Federal Republic of Germany %A Michel Kerszberg %A Aviv Bergman %T The Evolution of Data Processing Abilities in Competing Automata %J Computer Simulation in Brain Science, Copenhagen, Denmark %D 1986 %E Manfred Kochen %E Harold M. Hastings %T Advances in Cognitive Science: Steps Toward Convergence %I Westview Press, Inc %S AAAS Selected Symposia Series %D 1988 %A Chris Langton %T Artificial Life: Electronics Frontier %J Electronic Engineering Times %X On the Los Alamos artificial life conference %E Christopher G. Langton %T Artificial Life: The Proceedings of an Interdisciplinary Workshop on the Synthesis and Simulation of Living Systems %Z held September 1987 at Los Alamos, New Mexico %S Santa Fe Institute Studies in the Science of Complexity %D 1989 %V VI %I Addison-Wesley %A Geoffrey F. Miller %A Peter M. Todd %A Shailesh U. Hegde %T Designing Neural Networks using Genetic Algorithms %J Proceedings of the Third International Conference on Genetic Algorithms %E J. David Schaffer %D 1989 %I Morgan Kaufmann %P 379-384 %X Use of interconnection/constraint matrices set by genetic search to instantiate ANNs to be trained by backprop %A E. Mjolsness %A D. H. Sharp %T A preliminary analysis of recursively generated networks %D 1986 %J Proc. American Institute of Physics \(em Special Issue on Neural Nets %A Eric Mjolsness %A David H. Sharp %A Bradley K. Alpert %T Scaling, Machine Learning, and Genetic Neural Nets %D 1988 %R YALEU/DCS/TR-613, Yale %R LA-UR-88-142, Los Alamos %A Eric Mjolsness %A David H. Sharp %A Bradley K. Alpert %T Genetic Parsimony in Neural Nets %J Snowbird '88 Abstracts %D 1988 %A Eric Mjolsness %A David H. Sharp %A Bradley K. Alpert %T Scaling, Machine Learning, and Genetic Neural Nets %D 1989 %J Advances in Applied Mathematics %V 10 %A David J. Montana %A Lawrence Davis %T Training Feedforward Neural Networks Using Genetic Algorithms %J Proceedings of the Third International Conference on Genetic Algorithms %E J. David Schaffer %D 1989 %I Morgan Kaufmann %A H. Muhlenbein %A J. Kindermann %T The Dynamics of Evolution and Learning - Towards Genetic Neural Networks %D pre-1989 %I German National Research Center for Computer Science %Z adr: Postfach 1240, D-5205; St. Augustin 1 %A H. Muhlenbein %A J. Kinermann %T The Dynamics of Evolution and Learning \(em Towards Genetic Neural Networks %B Connectionism in Perspective %E R. Pfeifer %E Z. Schreter %E F. Fogelman-Soulie %E L. Steels %D 1989 %I Elsevier Science Publishers B.V. (North-Holland) %P 173-197 %A G. Deon Oosthuizen %T Machine Learning: A mathematical framework for neural network, sybmolic and genetics-based learning %J Proceedings of the Third International Conference on Genetic Algorithms %E J. David Schaffer %D 1989 %I Morgan Kaufmann %P 385-390 %X Shows equivalences between ANNs, GAs, and symbolic AI learning models. %A U. Ramacher %A M. Wesseling %T A Geometrical Approach to Neural Network Design %X possible analogy to developmental neuro-biology %J International Joint Conference on Nerual Networks %D 1989 %A Gerard Rinkus %T Learning as Natural Selection in a Sensori-Motor Being %I Dept. of Math & Computer Science, Adelphi University %A Rod Rinkus %T Learning and Pattern Recognition in Sensori-Motor Beings %D 1986 %I unpublished masters thesis, Hofstra University %A Mike Rudnick %T A Bibliography: The Intersection of Genetic Search and Artificial Neural Networks %D 1990 %R CS/E 90-001 %I Department of Computer Science and Engineering, Oregon Graduate Institute %A J. David Schaffer %A Richard A. Caruana %A Larry J. Eshelman %T Using Genetic Search to Exploit the Emergent Behavior of Neural Networks %C Los Alamos, NM %D 1990 %J Proceedings of the Emergent Computation 1989 Conference %E Stephanie Forest %E Selverston %T Model Neural Networks and Behaviour %D 1985 %I Plenum Press %X Contains section on neural deveolopment, but it's pretty biological and technical. %A John Maynard Smith %T When learning guides evolution %D 29 October 1987 %J Nature %P 761-762 %V 329 %A Branko Soucek %A Marina Soucek %T Neural and Massively Parallel Computers %D 1988 %I Wiley %X Broad overview. Includes ann and ga along with lots of other stuff. %A Peter Todd %T Evolutionary methods for connectionist architectures %D 1988 %I Psychology Department, Stanford University %A A. M. Uttley %T The probability of neural connexions %D 1955 %P 229-240 %Z march 1955, but what journal? %A C. H. Waddington %T Canalization of development and the inheritance of acquired characters %J Nature %D 1942 %V 150 %P 563-565 %A S. Waner %A H. M. Hastings %T Evolutionary learning of complex modes of information processing %D 1985 %A Darrell Whitley %T Applying Genetic Algorithms to Neural Network Problems: A Preliminary Report %D 1988 %I Computer Science Dept., Colorado State University %Z Fort Collins, Colorado 80523 %A D. Whitley %T Applying Genetic Algorithms to Neural Network Learning %D 1989 %J Proc. 7th Conf. for the Study of Artificial Intelligence and Simulated Behavior %C Sussex, England %I Pitman Publishing %A D. Whitley %A T. Starkweather %T Genetic Algorithm Applications: Neural Nets, Traveling Salesmen and Schedules %D 1989 %J 1989 Rocky Mountain Conference on Artificial Intelligence %C Denver, CO %A D. Whitley %T Optimizing Neural Networks Using Genetic Algorithms %D 1989 %J Special Neurocomputing Issue of Design & Elektronik %I Markt & Technik %C Munich, Germany %A D. Whitley %A T. Hanson %T Optimizing Neural Networks Using Faster, More Accurate Genetic Search %D 1989 %X This is a longer version of two papers we have submitted to conferences. It summarizes most of the work we have done in the past year. It also explains how we increased genetic search speed by more than 10 fold and achieved MORE ACCURATE solutions, typically 10e-10. %A Darrell Whitley %A Thomas Hanson %T Optimizing Neural Networks Using Faster, More Accurate Genetic Search %J Proceedings of the Third International Conference on Genetic Algorithms %E J. David Schaffer %D 1989 %I Morgan Kaufmann %P 391-396 %X Training backprops using GA. %A Darrell Whitley %A Timothy Starkweather %A Christopher Bogart %T Genetic Algorithms and Neural Networks: Optimizing Connections and Connectivity %R CS-89-117 (subsumes CS-89-113 & CS-89-114) %D 1989 %A S. W. Wilson %T Knowledge growth in an artificial animal %C Pittsburgh, PA %D 1985 %J Proc. of an Intl. Conf. on Genetic Algorithms and Their Applications %I Morgan Kaufmann %A S. W. Wilson %T Genetic algorithms and biological development %C Cambridge, MA %D 1987 %J Proc. Second Intl. Conf. on Genetic Algorithms and Their Applications %I Morgan Kaufmann %A Stewart W. Wilson %T Preceptron Redux: Emergence of Structure %D 1990 %J Proceedings of the Emergent Computation 1989 Conference %E Stephanie Forest %X Stuart uses genetic search (GS) to set the interconnect between the inputs and the sigma-pi nodes of the perceptron. In effect, GS is used to determine what features the perceptron looks at.