Abstract
Evolutionary computation is a class of global search techniques based on the learning process of a population of potential solutions to a given problem, that has been successfully applied to a variety of problems. In this paper a new approach to the construction of neural networks based on evolutionary computation is presented. A linear chromosome combined to a graph representation of the network are used by genetic operators, which allow the evolution of the architecture and the weights simultaneously without the need of local weight optimization. This paper describes the approach, the operators and reports results of the application of this technique to several binary classification problems.
Similar content being viewed by others
References
S. Haykin. Neural networks, a comprehensive foundation. Macmillan College Publishing Company, Inc., 866 Third Avenue, New York, New York 10022, 1994.
R. Reed. Pruning algorithms: a survey. IEEE Transactions on Neural Networks, 4(5):740- 747, 1993.
M. Frean. The upstart algorithm: a method for constructing and training feed-forward neural networks. Neural Computation, 2:198- 209, 1990.
S. E. Fahlman and C. Lebiere. The cascade-correlation learning architecture. In D. Touretzky, editor, Advances in Neural Information Processing Systems, volume 2, pages 524- 532. Morgan Kaufmann, 1990.
D. Chen, C. Giles, G. Sun, H. Chen, Y. Less, and M. Goudreau. Constructive learning of recurrent neural networks. In IEEE International Conference on Neural Networks (ICNN), pages 1196- 1201, 1993.
C. Campbell and C. Vicente. The target switch algorithm: a constructive learning procedure for feed-forward neural networks. Neural Computation, 7:1245- 1264, 1995.
X. Yao. An overview of evolutionary computation. Chinese Journal of Advanced Software Research, 3(1), 1996. To be published.
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, Massachusetts, 1989.
M. Mitchell. An introduction to genetic algorithms. MIT Press, Cambridge, Massachusetts, USA, 1996.
L. Davis. Handbook of Genetic Algorithms. Van Nostrand Rheinhold, New York, NY, 1991.
Michalewicz Zbigniew. Genetic Algorithms [plus] Data Structures = Evolution Programs. Springer-Verlag, Berlin, 1994.
S. Harp, T. Samad, and A. Guha. Toward the genetic synthesis of neural networks. In J. Schaffer, editor, Proceedings of the 3rd International Conference on Genetic Algorithms (ICGA), pages 360- 369, San Mateo, CA, USA, 1989.
M. Mandischer. Evolving recurrent neural networks with non-binary encoding. In Proceedings of the 2nd IEEE Conference on Evolutionary Computation (ICEC), volume 2, pages 584- 589, Perth, Australia, Nov. 1995.
M. Mandischer. Representation and evolution of neural networks. In Proceedings of the International Conference on Artificial Neural Nets and Genetic Algorithms (ICANNGA), pages 643- 649, 1993.
H. Kitano. Neurogenetic learning: an integrated method of designing and training neural networks using genetic algorithms. Physica D, 75:225- 238, 1994.
S. Fujita and H. Nishimura. An evolutionary approach to associative memory in recurrent neural networks. Neural Processing, 1(2), 1994.
H. Braun and P. Zagorski. ENZO-M-a hybrid approach for optimizing neural networks by evolution and learning. In Y. Davidor, H. Schwefel, and H. Manner, editors, Parallel Problem Solving from Nature (PPSN3), volume 866. Springer-Verlag, 1994. Lecture Notes in Computer Science.
X. Yao and J. Liu. Evolutionary artificial neural networks that learn and generalize well. In Proceedings of the 1996 IEEE International Conference on Neural Networks, Washington, DC, Jun. 1996. Submitted.
V. Maniezzo. Genetic evolution of the topology and weight distribution of neural networks. IEEE Transactions on Neural Networks, 5(1):39- 53, Jan. 1994.
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.
S. Nolfi and D. Parisi. Growing neural networks. Technical Report PCIA-95-15, Rome, Italy, Jun. 1991.
B. T. Zhang and H. Mühlenbein. Evolving optimal neural networks using genetic algorithms with Occam's razor. Complex Systems, 7(3):199- 220, 1993.
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). IEEE Press, 1993.
J. McDonnell and D. Waagen. Evolving neural network connectivity. In Proceedings of IEEE International Conference on Neural Networks (ICNN), pages 863- 868, San Francisco, CA, USA, 1993.
J. Holland. Adaptation in natural and artificial systems. University of Michigan Press, Ann Arbor, Michigan, 1975.
J. R. Koza. Genetic Programming, on the Programming of Computers by Means of Natural Selection. The MIT Press, Cambridge, Massachusetts, 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.
B. Zhang and Muehlenbein. Synthesis of sigma-pi neural networks by the breeder genetic programming. In Proceedings of IEEE International Conference on Evolutionary Computation (ICEC),World Congress on Computational Intelligence, pages 318- 323, Orlando, Florida, USA, Jun. 1994. IEEE Computer Society Press.
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.
R. Poli. Some steps towards a form of parallel distributed genetic programming. In Proceedings of the First On-line Workshop on Soft Computing, 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.
X. Yao and Y. Shi. A preliminary study on designing artificial neural networks using co-evolution. In Proceedings of the IEEE Singapore International Conference on Intelligent Control and Instrumentation, pages 149- 154, Jun. 1995.
K. Tang, C. Chan, K. Man, and S. Kwong. Genetic structure for NN topology and weights optimization. In Proceedings of the International Conference on Genetic Algorithms in Engineering Systems: innovations and applications (GALESIA), pages 250- 255, Sept. 1995.
D. Dasgupta and D. McGregor. Designing application-specific neural networks using the structured genetic algorithm. In L. Whitley and J. Schaffer, editors, Proceedings of International Workshop on Combinations of Genetic Algorithms and Neural Networks (COGANN), pages 87- 96. IEEE Computer Society Press, Jun. 1992.
D. Whitley, T. Starkweather, and C. Bogart. Genetic algorithms and neural networks: Optimizing connections and connectivity. Parallel Computing, 14-3:347- 361, 1990.
D. Rumelhart and J. McClelland. Parallel Distributed Processing. IEEE Press, Piscataway, NJ, USA, 1986.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Pujol, J.C.F., Poli, R. Evolving the Topology and the Weights of Neural Networks Using a Dual Representation. Applied Intelligence 8, 73–84 (1998). https://doi.org/10.1023/A:1008272615525
Issue Date:
DOI: https://doi.org/10.1023/A:1008272615525