Abstract
There are numerous algorithms available for training artificial neural networks. Besides classical algorithms for supervised learning such as backpropagation, associative memory and radial basis function, this training task can be employed by evolutionary computation since most of the gradient descent related algorithms can be view as an application of optimization theory and stochastic search. In this paper, the logistic model of population growth from ecology is integrated into initialization, selection and crossover operators of genetic algorithms for neural network training. These chaotic operators are very efficient in maintaining the population diversity during the evolution process of genetic algorithms. A comparison is done on the basis of a benchmark comprising several data classification problems for neural networks. Three variants of training – Backpropagation (BP), Genetic Algorithms (GA) and Genetic Algorithms with Chaotic Operators (GACO) – are described and compared. The experimental results confirm the dynamic mobility of chaotic algorithms in GACO network training, which can overcome saturation and improve the convergence rate.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Carlo, M.F., Peter, J.F.: An Overview of Evolutionary Algorithms in Multiobjective Optimization. Evolutionary Computation 3(1), 1–16 (1995)
Fredric, M.H., Ivica, K.: Principles of Neurocomputing for Science and Engineering, pp. 106–110. McGraw-Hill International Edition, New York (2000)
Liao, G.C.: Hybrid Chaos Search Genetic Algorithm and Meta-Heuristics Method for Short-Term Load Forecasting. Electrical Engineering 88, 165–176 (2006)
James, C.S.L.: Introduction to Stochastic Search and Optimization – Estimation, Simulation and Control. Wiley-Interscience Series, pp. 22–25 (2006)
Lu, H.J., Zhang, H.M., Ma, L.H.: A New Optimization Algorithm Based on Chaos. Journal of Zhengjiang University Science A 7(4), 539–542 (2006)
Paulo, J.G.L., et al.: Artificial Neural Networks in Biomedicine. Springer, London (2000)
Robert, L.D.: A First Course in Chaotic Dynamical Systems, pp. 114–120. Addison-Wesley Publishing Company, Reading (1992)
Maniezzo, V.: Genetic Evolution of the Topology and Weight Distribution of Neural Networks. IEEE Transactions on Neural Networks 5(1), 39–53 (1994)
Wang, S.A., Guo, Z.L.: Application of A Novel Fuzzy Clustering Method Based on Chaos Immune Evolutionary Algorithm for Edge Detection in Image Processing. In: Front. Mech. Eng. China, vol. 1, pp. 85–89. Higher Education Press and Springer-Verlag, Heidelberg (2006)
Yan, W., et al.: Hybrid Genetic / BP Algorithm and Its Application for Radar Target Classification. In: Proceeding of the 1997 IEEE National Aerospace and Electronics Conference (NAECON), pp. 981–984. IEEE Press, USA (1997)
Zuo, X.Q., Li, S.Y.: The Chaos Artificial Immune Algorithm and Its Application to RBF Neuro-Fuzzy Controller Design. IEEE, Los Alamitos (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Leong, K.Y., Sitiol, A., Anbananthen, K.S.M. (2009). Enhance Neural Networks Training Using GA with Chaos Theory. In: Yu, W., He, H., Zhang, N. (eds) Advances in Neural Networks – ISNN 2009. ISNN 2009. Lecture Notes in Computer Science, vol 5552. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-01510-6_59
Download citation
DOI: https://doi.org/10.1007/978-3-642-01510-6_59
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-01509-0
Online ISBN: 978-3-642-01510-6
eBook Packages: Computer ScienceComputer Science (R0)