Abstract
This paper presents a new approach to evolutionary artificial neural networks, based on the integration of feedforward neural networks, messy genetic algorithms (GAs), and singular value decomposition (SVD). The set of competing hidden nodes with variable number of connections from the input layer represents an evolving neural network. Selection of hidden nodes is based on their estimation via SVD. The resulting singular values are used to determine significance of hidden nodes for the network's output. To represent connectivity of hidden nodes and to process the topology of connections between input and hidden layers, we employ the approach of messy GAs. This establishes a framework for processing strings of variable length which codes this topology and allows one to search for useful combinations of input variables. The proposed approach is tested using sonar data classification.
Preview
Unable to display preview. Download preview PDF.
References
Schaffer, J.D., Whitley, D., and Eshelman, L.J., “Combinations of genetic algorithms and neural networks: A survey of the state of the art,” Combinations of Genetic Algorithms and Neural Networks (Whitley, L.D., Schaffer, J.D., eds.), 1–37, Los Alamitos, CA: IEEE Computer Society Press, June 1992.
Yao, X., “A review of evolutionary artificial neural networks,” International Journal of Intelligent Systems, 8(4), 539–567, 1993.
Smith, R., Cribbs III, H.B., “Is a learning classifier system a type of neural network?,” Evolutionary Computation, 2(1), 19–36, 1994.
Smalz, R., Conrad, M., “Combining evolution with credit apportionment: a new learning algorithm for neural nets,” Neural Networks, 7(2), 341–351, 1994.
Finnoff, W., Hergert, F., Zimmermann, H.G., “Improving model selection by nonconvergent methods,” Neural Networks, 6, 771–783.
Fahlman, S.E. and Lebiere, C., “The cascade-correlation learning architecture,” Advances in Neural Information Processing Systems, 2, (Lippmann, R.P., Moody, J.E., Touretzky, D.S., eds.), 524–532, San Francisco: Morgan Kaufmann, 1991.
Goldberg, D., Deb, K., and Korb, B., “Messy genetic algorithms: Motivation, analysis, and first results,” Complex Systems, 3, 493–530, 1989.
Goldberg, D., Deb, K., and Korb, B., “Messy genetic algorithms revisited: Studies in mixed size and scale,” Complex Systems, 4, 415–444, 1990.
Forsythe, G.E., Malcolm, M.A., and Moler, C.B., Computer methods for mathematical computations, Prentice-Hall, Inc., 1977.
Fahlman, S.E., “An empirical study of learning speed in back-propagation networks,” Carnegie Mellon University Technical Report CMU-CS-88-162, September 1988.
Rumelhart, D.E., Hinton, G.E., and Williams, R.J., “Learning internal representations by error propagation,” In: Parallel Distributed Processing, MIT Press, 1, 318–362, 1986.
Goldberg, D.E., Genetic algorithms in search optimization and machine learning, Reading, MA, Addison-Wesley, 1989.
Back, T., Hoffmeister, F., Schwefel H.-P., “A survey of evolutionary strategies,” Proceedings of the 4th International Conference on Genetic Algorithms and their Applications, edited by Belew R.K. and Booker L.B., pp. 2–9, 1991, Morgan Kaufmann, San Mateo, CA.
Gorman, R.P., and Sejnowski, T.J., “Analysis of hidden units in a layered network trained to classify sonar targets,” Neural Networks, 1, 75–89, 1988.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Skourikhine, A.N. (1998). An evolutionary algorithm for designing feedforward neural networks. 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/BFb0040814
Download citation
DOI: https://doi.org/10.1007/BFb0040814
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