Abstract
Training artificial neural networks is a complex task of great practical importance. Besides classical ad-hoc algorithms such as backpropagation, this task can be approached by using Evolutionary Computation, a highly configurable and effective optimization paradigm. This chapter provides a brief overview of these techniques, and shows how they can be readily applied to the resolution of this problem. Three popular variants of Evolutionary Algorithms —Genetic Algorithms, Evolution Strategies and Estimation of Distribution Algorithms— are described and compared. This comparison is done on the basis of a benchmark comprising several standard classification problems of interest for neural networks. The experimental results confirm the general appropriateness of Evolutionary Computation for this problem. Evolution Strategies seem particularly proficient techniques in this optimization domain, and Estimation of Distribution Algorithms are also a competitive approach.
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
Alander, J. T. (1994). Indexed bibliography of genetic algorithms and neural networks. Technical Report 94–1-NN, University of Vaasa, Department of Information Technology and Production Economics.
Bäck, T. (1996). Evolutionary Algorithms in Theory and Practice. Oxford University Press, New York.
Baluja, S. (1995). An empirical comparison of seven iterative and evolutionary function optimization heuristics. Technical Report CMU-CS-95–193, Carnegie Mellon University.
Berlanga, A., Isasi, P., Sanchís, A., and Molina, J. M. (1999a). Neural networks robot controller trained with evolution strategies. In Proceedings of the 1999 Congress on Evolutionary Computation, pages 413–419, Washington D. C. IEEE Press.
Berlanga, A., Molina, J. M., Sanchís, A., and Isasi, P. (1999b). Applying evolution strategies to neural networks robot controllers. In Mira, J. and Sánchez-Andrés, J. V., editors, Engineering Applications of Bio-Inspired Artificial Neural Networks, volume 1607 of Lecture Notes in Computer Science, pages 516–525. Springer-Verlag, Berlin.
Beyer, H.-G. (1993). Toward a theory of evolution strategies: Some asymptotical results from the (1+005C)-theory. Evolutionary Computation, 1(2):165–188.
Beyer, H.-G. (1995). Toward a theory of evolution strategies: The (µ,))-theory. Evolutionary Computation, 3(1):81–111.
Beyer, H.-G. (1996). Toward a theory of evolution strategies: Self adaptation. Evolutionary Computation, 3(3):311–347.
Castillo, P. A., González, J., Merelo, J. J., Prieto, A., Rivas, V., and Romero, G. (1999). GA-Prop-II: Global optimization of multilayer perceptrons using GAs. In Proceedings of the 1999 Congress on Evolutionary Computation, pages 2022–2027, Washington D. C. IEEE Press.
Caudell, T. P. and Dolan, C. P. (1989). Parametric connectivity: training of constrained networks using genetic algoritms. In Schaffer, J. D., editor, Proceedings of the Third International Conference on Genetic Algorithms, pages 370–374, San Mateo, CA. Morgan Kaufmann.
Davis, L. (1991). Handbook of Genetic Algorithms. Van Nostrand Reinhold Computer Library, New York.
Fogel, D. B., Fogel, L. J., and Porto, V. W. (1990). Evolving neural networks. Biological Cybernetics, 63:487–493.
Galic, E. and Höhfeld, M. (1996). Improving the generalization performance of multi-layer-perceptrons with population-based incremental learning. In Parallel Problem Solving from Nature IV, volume 1141 of Lecture Notes in Computer Science, pages 740–750. Springer-Verlag, Berlin.
Gallagher, M. R. (2000). Multi-layer Perceptron Error Surfaces: Visualization, Structure and Modelling. PhD thesis, Department of Computer Science and Electrical Engineering, University of Queensland.
Gruau, F. and Whitley, D. (1993). Adding learning to the cellular development of neural networks: Evolution and the baldwin effect. Evolutionary Computation, 1:213–233.
Herrera, F., Lozano, M., and Verdegay, J. L. (1996). Dynamic and heuristic fuzzy connectives-based crossover operators for controlling the diversity and convengence of real coded genetic algorithms. Journal of Intelligent Systems, 11:1013–1041.
Holland, J. H. (1975). Adaptation in Natural and Artificial Systems. University of Michigan Press, Ann Harbor.
Jones, T. C. (1995). Evolutionary Algorithms,Fitness Landscapes and Search. PhD thesis, University of New Mexico.
Larrañaga, P. (2001). A review on Estimation of Distribution Algorithms. In Larrañaga, P. and Lozano, J. A., editors, Estimation of Distribution Algorithms: A new tool for Evolutionary Computation. Kluwer Academic Publishers.
Mangasarian, O. L. and Wolberg, W. H. (1990). Cancer diagnosis via linear programming. SIAM News, 23(5):1–18.
Maxwell, B. and Anderson, S. (1999). Training hidden Markov models using population-based learning. In Banzhaf, W. et al., editors, Proceedings of the 1999 Genetic and Evolutionary Computation Conference, page 944, Orlando FL. Morgan Kaufmann.
McClelland, J. L. and Rumelhart, D. E. (1986). Parallel Distributed Processing: Explorations in the Microstructure of Cognition. The MIT Press.
Montana, D. and Davis, L. (1989). Training feedforward neural networks using genetic algorithms. In Proceedings of the Eleventh International Joint Con- ference on Artificial Intelligence, pages 762–767, San Mateo, CA. Morgan Kaufmann.
Moscato, P. (1999). Memetic algorithms: A short introduction. In Corne, D., Dorigo, M., and Glover, F., editors, New Ideas in Optimization, pages 219234. McGraw-Hill.
Mühlenbein, H. and Paaß, G. (1996). From recombination of genes to the es-timation of distributions i. binary parameters. In H. M. Voigt, e. a., editor,Parallel Problem Solving from Nature IV, volume 1141 of Lecture Notes in Computer Science, pages 178–187. Springer-Verlag, Berlin.
Nakai, K. and Kanehisa, M. (1992). A knowledge base for predicting protein localization sites in eukaryotic cells. Genomics, 14:897–911.
Rechenberg, I. (1973). Evolutionsstrategie: Optimierung technischer Systeme nach Prinzipien der biologischen Evolution. Frommann-Holzboog Verlag, Stuttgart.
Ribeiro, B., Costa, E., and Dourado, A. (1995). Lime kiln fault detection and diagnosis by neural networks. In Pearson, D. W., Steele, N. C., and Albrecht, R. F., editors, Artificial Neural Nets and Genetic Algorithms 2, pages 112115, Wien New York. Springer-Verlag.
Rosenblatt, F. (1959). Principles of Neurodynamics. Spartan Books, New York.
Rumelhart, D. E., Hinton, G. E., and Williams, R. J. (1986). Learning representations by backpropagating errors. Nature, 323:533–536.
Schwefel, H.-P. (1977). Numerische Optimierung von Computer-Modellen mittels der Evolutionsstrategie, volume 26 of Interdisciplinary Systems Research. Birkhäuser, Basel.
Silva, F. M. and Almeida, L. B. (1990). Speeding up backpropagation. In Eck-miller, R., editor, Advanced Neural Computers. North Holland.
Whitley, D. (1999). A free lunch proof for gray versus binary encoding. In Banzhaf, W. et al., editors, Proceedings of the 1999 Genetic and Evolutionary Computation Conference, pages 726–733, Orlando FL. Morgan Kaufmann.
Whitley, D. and Hanson, T. (1989). Optimizing neural networks using faster, more accurate genetic search. In Schaffer, J. D., editor, Proceedings of the Third International Conference on Genetic Algorithms, pages 391–396, San Mateo, CA. Morgan Kaufmann.
Whitley, D., Mathias, K., and Fitzhorn, P. (1991). Delta coding: An iterative search strategy for genetic algorithms. In Belew, R. K. and Booker, L. B., editors, Proceedings of the Fourth International Conference on Genetic Algorithms, pages 77–84, San Mateo CA. Morgan Kaufmann.
Whitley, D., Starkweather, T., and Bogart, B. (1990). Genetic algorithms and neural networks: Optimizing connections and connectivity. Parallel Computing, 14:347–361.
Wienholt, W. (1993). Minimizing the system error in feedforward neural networks with evolution strategy. In Gielen, S. and Kappen, B., editors, Proceedings of the International Conference on Artificial Neural Networks, pages 490–493, London. Springer-Verlag.
Wolpert, D. H. and Macready, W. G. (1997). No free lunch theorems for opti-mization. IEEE Transactions on Evolutionary Computation, 1(1):67–82.
Yang, J.-M., Horng, J.-T., and Kao, C.-Y. (1999). Incorporation family competition into Gaussian and Cauchy mutations to training neural networks using an evolutionary algorithm. In Proceedings of the 1999 Congress on Evolutionary Computation, pages 1994–2001, Washington D. C. IEEE Press.
Zhang, B.-T. and Cho, D.-Y. (2000). Evolving neural trees for time series prediction using Bayesian evolutionary algorithms. In Proceedings of the First IEEE Workshop on Combinations of Evolutionary Computation and Neural Networks (ECNN-2000).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer Science+Business Media New York
About this chapter
Cite this chapter
Cotta, C., Alba, E., Sagarna, R., Larrañaga, P. (2002). Adjusting Weights in Artificial Neural Networks using Evolutionary Algorithms. In: Larrañaga, P., Lozano, J.A. (eds) Estimation of Distribution Algorithms. Genetic Algorithms and Evolutionary Computation, vol 2. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-1539-5_18
Download citation
DOI: https://doi.org/10.1007/978-1-4615-1539-5_18
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-5604-2
Online ISBN: 978-1-4615-1539-5
eBook Packages: Springer Book Archive