Abstract
This paper presents a new approach to the evolution of neural networks. A linear chromosome combined with a grid-based representation of the network and a new crossover operator allow the evolution of the architecture and the weights simultaneously. There is no need for a separate weight optimization procedure and networks with more than one type of activation function can be evolved. This paper describes the representation, the crossover operator, and reports on results of the application of the method to evolve a neural controller for the pole-balancing problem.
Preview
Unable to display preview. Download preview PDF.
References
D. Fogel. Evolutionary computation: toward a new philosophy of machine Intelligence. IEEE Press, Piscataway, NJ, USA, 1995.
D. Goldberg. Genetic algorithm in search, optimization and machine learning. Addison-Wesley, Reading, Massachusets, 1989.
P. J. Angeline, G. M. Saunders, and J. B. Pollack. An evolutionary algorithm that constructs recurrent neural networks. IEEE Transactions on Neural Networks, 5(1), 1994.
D. Fogel. Using evolutionary programming to create neural networks that are capable of playing Tic Tac Toe. In IEEE International Conference on Neural Networks (ICNN), pages. 875–880. IEEE Press, 1993.
J. McDonnell and D. Waagen. Neural network structure design by evolutionary programming. In D. Fogel and W. Atmar, editors, Proceedings of the Sec. Annual Conference on Evolutionary Programming, pages 79–89, La Jolla, CA, USA, Feb. 1993. Evolutionary Programming Society.
V. Maniezzo. Genetic evolution of the topology and weight distribution of neural networks. IEEE Transactions on Neural Networks, 5(1):39–53, 1994.
D. Whitley, S. Dominic, R. Das, and C. Anderson. Genetic reinforcement learning for neurocontrol problems. Machine Learning, 13:259–284, 1993.
J. R. Koza. Genetic Programming, on the Programming of Computers by Means of Natural Selection. The MIT Press, Cambridge, Massachusets, 1992.
B. Zhang and H. Muehlenbein. Genetic programming of minimal neural nets using Occam's razor. In S. Forrest, editor, Proceedings of the 5th international conference on genetic algorithms (ICGA'93), pages 342–349. Morgan Kaufmann, 1993.
F. Gruau. Neural network synthesis using cellular encoding and the genetic algorithm. PhD thesis, Laboratoire de L'informatique du Parallélisme, Ecole Normale Supériere de Lyon, Lyon, France, 1994.
R. Poli. Some steps towards a form of parallel distributed genetic programming. In Proceedings of the First On-line Workshop on Soft Computing, pages 290–295, Aug. 1996.
R. Poli. Discovery of symbolic, neuron-symbolic and neural networks with parallel distributed genetic programming. In 3rd International Conference on Artificial Neural Networks and Genetic Algorithms (ICANNGA), 1997.
J. C. F. Pujol and R. Poli. Evolution of the topology and the weights of neural networks using genetic programming with a dual representation. Technical report CSRP-97-07, The University of Birmingham, School of Computer Science, 1997.
D. Whitley, F. Gruau, and L. Pyeatt. Cellular encoding applied to neurocontrol. In Proceedings of 6th International Conference on Genetic Algorithms, pages 460–467. Morgankaufmann, 1995.
F. Gruau, D. Whitley, and L. Pyeatt. A comparison between cellular encoding and direct encoding for genetic neural networks. In J. Koza, D. Goldberg, D. Fogel, and R. Riolo, editors, Genetic Programming 1996: Proceedings of the First Annual Conference, pages 81–89, Stanford University, CA, USA, Jul. 1996. MIT Press.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pujol, J.C.F., Poli, R. (1998). Dual network representation applied to the evolution of neural controllers. In: Porto, V.W., Saravanan, N., Waagen, D., Eiben, A.E. (eds) Evolutionary Programming VII. EP 1998. Lecture Notes in Computer Science, vol 1447. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0040815
Download citation
DOI: https://doi.org/10.1007/BFb0040815
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64891-8
Online ISBN: 978-3-540-68515-9
eBook Packages: Springer Book Archive