Abstract
This paper proposes an evolutionary learning algorithm to discipline the projection neural networks (PNNs) which can activate radial basis functions as well as sigmoid functions with special type of hidden nodes. The proposed algorithm not only trains the parameters and the connection weights but also optimizes the network structure. Through structure optimization, the number of hidden nodes necessary to represent a given target function is determined and the role of each hidden node as an activator of a radial basis function or a sigmoid function is decided. In order to apply the algorithm, PNN is realized by a self-organizing genotype representation with a linked list data structure. Simulations show that the algorithm can build the PNN with less hidden nodes than the existing learning algorithm which uses the error back propagation(EBP) and the network growing strategy.
Preview
Unable to display preview. Download preview PDF.
References
J.S.Judd: Neural Network Design and the Complexity of Learning, MIT Press-Bradford Book, Cambridge, MA,1990
Martin Mandischer: Representation and Evolution of Neural Networks, Department of Computer Science, University of Dotmund,Germany
M.Hirahara, N.Oka: A hybrid model composed of a multilayer perceptron and a radial basis function network, Procs. of IJCNN,Nagoya, vol.1,pp.1353–1356,1993
R.M.Kil, J.Y.Choi: Time series prediction based on global and local estimation models, WCNN,vol.4,pp.617–621, July 1993
S.Park,L.J.Park, C.H.Park: Structural hybrid of multilayer neural networks and Gaussian potential function networks, Procs. of ICONIP,vol.3, pp.1393–1397,Seoul,Oct 1994
G.D.Wilensky, N.Manukan: The Projection neural networks, Procs. of IJCNN,Baltimore,vol.2, pp.II–358-II–367,1992
Byeong-Kap Choi, Chong-Ho Choi, Jin-Young Choi: Projection Neural Networks for Function Approximation, KIEE,Vol. 44, pp.961–968,1995.7
D.E.Goldberg: Genetic Algorithms in Search, Optimization and Machine Learning, Addison-Wesley, 1989.
Z.Michalewicz, T.D.Logan, S.Swaminathan: Evolutionary Operators for Continuous Convex Parameter Spaces, Proceedings of the Third Annual Conference on Evolutionary Programming, pp.84–97, San Diego California, 1994.
Mukesh J.Patel: Heuristical Constraints on Search Complexity for Multi-modal Non-optimal Models, IEEE Press, pp.164–180,1995
Gunter Rudolph: Convergence analysis of canonical genetic algorithms, IEEE Transactions on Neural Networks, Vol.5,No.1,January,1994.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hwang, M.W., Choi, J.Y. (1997). Evolutionary learning algorithm for projection neural networks. In: Yao, X., Kim, JH., Furuhashi, T. (eds) Simulated Evolution and Learning. SEAL 1996. Lecture Notes in Computer Science, vol 1285. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0028530
Download citation
DOI: https://doi.org/10.1007/BFb0028530
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63399-0
Online ISBN: 978-3-540-69538-7
eBook Packages: Springer Book Archive