Abstract
Many traditional methods for training neural networks using genetic algorithms and genetic programming do not have any special provisions for taking advantage of decomposable problems which can be solved by combining solutions to each subproblem. This paper describes a new approach to neural network construction using genetic programming which is designed to rapidly construct networks composed of similar subnetworks. A system has been developed to produce trained weightless neural networks by using construction rules to build the networks. The network construction rules are evolved by the genetic programming system. The system has been applied to decomposable Boolean problems and the results were compared with a modified version of the system in which networks cannot be constructed modularly. The modular version of the system obtains significantly better results than the non-modular version of the program.
Brett Talko is now with the Defence Science and Technology Organisation, 506 Lorimer Street, Fishermans Bend, Victoria 3207, Australia.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Richard K. Belew, John McInerney, and Nicol N. Schraudolph. Evolving networks: Using the genetic algorithm with connectionist learning. In Christopher G. Langton, Charles Taylor, J. Doyne Farmer, and Steen Rasmussen, editors, Artificial Life II. Proceedings of the Workshop on Artificial Life, pages 511–547, Santa Fe, New Mexico, 1991. Addison-Wesley.
Egbert J. W. Boers and Herman Kuiper. Biological metaphors and the design of modular artificial neural networks. Master’s thesis, Departments of Computer Science and Experimental and Theoretical Psychology, Leiden University, The Netherlands, 1992.
Toshio Fukuda, Tadashi Kohno, and Takanori Shibata. Dynamic memory by recurrent neural network and its learning by genetic algorithm. In Proceedings of the 32nd Conference on Decision and Control, volume 3, pages 2815–2820, San Antonio, Texas, 15–17 December 1993. IEEE Press.
Frédéric Gruau. Cellular encoding of genetic neural networks. Technical Report RR92-21, Laboratoire de l’Informatique du Parallélisme, Ecole Normale Supérieure de Lyon, France, May 1992.
Frédéric Gruau. Neural Network Synthesis Using Cellular Encoding and the Genetic Algorithm. PhD thesis, Laboratoire de l’Informatique du Parallélisme, Ecole Normale Supérieure de Lyon, France, 4 January 1994.
Steven Alex Harp, Tariq Samad, and Aloke Guha. Towards the genetic synthesis of neural networks. In J. David Schaffer, editor, Proceedings of the Third International Conference on Genetic Algorithms, pages 360–369, George Mason University, Washington D.C., 4–7 June 1989. Morgan Kaufmann.
Hiroaki Kitano. Designing neural networks using genetic algorithms with graph generation system. Complex Systems, 4:461–476, August 1990.
Martin Mandischer. Representation and evolution of neural networks. In R. F. Albrecht, C. R. Reeves, and N. C. Steele, editors, Artificial Neural Nets and Genetic Algorithms: Proceedings of the International Conference, pages 643–649, Innsbruck, Austria, 1993. Springer-Verlag, Wien and New York.
Geoffrey F. Miller, Peter M. Todd, and Shailesh U. Hegde. Designing neural networks using genetic algorithms. In J. David Schaffer, editor, Proceedings of the Third International Conference on Genetic Algorithms, pages 379–384, George Mason University, Washington D.C., 4–7 June 1989. Morgan Kaufmann.
David J. Montana and Lawrence Davis. Training feedforward neural networks using genetic algorithms. In Proceedings of the Eleventh International Joint Conference on Artificial Intelligence, volume 1, pages 762–767, Detroit, Michigan, 20–25 August 1989.
Stefano Nolfi and Domenico Parisi. “Genotypes” for neural networks. In Michael A. Arbib, editor, The Handbook of Brain Theory and Neural Networks, pages 431–434. The MIT Press, 1995.
J. Santos and R. J. Duro. Evolutionary generation and training of recurrent artificial neural networks. In Zbigniew Michalewicz, editor, Proceedings of the 1st IEEE Conference on Evolutionary Computation, volume 2, pages 759–763, Orlando, Fla, 27–29 June 1994. IEEE Press.
Bret Talko. Evolving modular neural networks using rule-based genetic programming. In Norman Foo, editor, 12th Australian Joint Conference on Artificial Intelligence, AI’99, volume 1747 of Advanced Topics in Artificial Intelligence. Lecture Notes in Artificial Intelligence, Sydney, Australia, 6–10 December 1999. Springer-Verlag.
Bret Talko. A rule-based approach for constructing neural networks using genetic programming. Master’s thesis, Department of Computer Science and Software Engineering, The University of Melbourne, Australia, March 1999.
Jan Torreele. Temporal processing with recurrent networks: An evolutionary approach. In Richard K. Belew and Lashon B. Booker, editors, Proceedings of the Fourth International Conference on Genetic Algorithms, pages 555–561, University of California, San Diego, 14–17 July 1991. Morgan Kaufmann.
Darrell Whitley, Stephen Dominic, and Rajarshi Das. Genetic reinforcement learning with multilayer neural networks. In Richard K. Belew and Lashon B. Booker, editors, Proceedings of the Fourth International Conference on Genetic Algorithms, pages 562–570, University of California, San Diego, 14–17 July 1991. Morgan Kaufmann.
Xin Yao. Evolutionary artificial neural networks. International Journal of Neural Systems, 4(3):203–222, September 1993.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Talko, B., Stern, L., Kitchen, L. (2000). Evolving Neural Networks for Decomposable Problems Using Genetic Programming. In: Mizoguchi, R., Slaney, J. (eds) PRICAI 2000 Topics in Artificial Intelligence. PRICAI 2000. Lecture Notes in Computer Science(), vol 1886. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44533-1_46
Download citation
DOI: https://doi.org/10.1007/3-540-44533-1_46
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67925-7
Online ISBN: 978-3-540-44533-3
eBook Packages: Springer Book Archive