Abstract
In this work, we proposed a method of artificial neural network learning using differential evolutionary(DE) algorithm. DE with global and local neighborhood based mutation(DEGL) algorithm is used to search the synaptic weight coefficients of neural network and to minimize the learning error in the error surface.DEGL is a version of DE algorithm in which both global and local neighborhood-based mutation operator is combined to create donor vector.The proposed method is applied for classification of real-world data and experimental results show the efficiency and effectiveness of the proposed method and also a comparative study has been made with classical DE algorithm.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Slowik, A.: Application of an Adaptive Differential Evolution With Multiple Trial Vectors to Artificial Neural Network Training. IEEE Transactions On Industrial Electronics 58(8), 3160–3167 (2011)
Das, S., Abraham, A., Chakrabarti, U.K., Konar, A.: Differential Evolution Using a Neighborhood-Based Mutation Operator. IEEE Transactions On Evolutionary Computation 13(3), 526–553 (2009)
Mingguang, L., Gaoyang, L.: Artificial Neural Network Co-optimization Algorithm based on Differential Evolution. In: Second International Symposium on Computational Intelligence and Design, pp. 256–559 (2009)
Slowik, A., Bialko, M.: Training of Artificial Neural Networks Using Differential Evolution Algorithm. In: 2008 Conference on Human System Interactions, pp. 60–65 (2008)
Gao, Y., Liu, J.: A Modified Differential Evolution Algorithm and Its Application in the Training of BP Neural Network. In: Proceedings of the 2008 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, Xi’an, China, pp. 1373–1377 (2008)
Lee, Y.S., Shamsuddin, S.M., Hamed, H.N.: Bounded PSO Vmax Function in Neural Network Learning. In: Eighth International Conference on Intelligent Systems Design and Applications, pp. 474–479. IEEE (2008)
Junyou, B.: Stock Price forecasting using PSO-trained neural networks. IEEE Congress on Evolutionary Computation, 2879–2885 (2007)
Price, K., Storn, R., Lampinen, J.: Dierential Evolution – A Practical Approach to Global Optimization. Springer, Heidelberg (2005)
Yan, H., Zheng, J., Jiang, Y., Peng, C., Li, Q.: Development of a Decision Support System for heart Disease Diagnosis using Multilayer Perceptron. In: Proceedings of the 2003 International Symposium on Circuits and Systems, pp. 709–712 (2003)
Fan, H.Y., Lampinen, J.: A Trigonometric Mutation Operation to Differential Evolution. International Journal of Global Optimization 27, 105–129 (2003)
Shi, Y., Eberhart, R.C.: A modified particle swarm optimizer. In: Proc. IEEE World Congr. Comput. Intell., pp. 69–73 (1998)
Tsi, D.-Y.: Classification of Heart Diseases in Ultrasonic Images using Neural Networks Trained by Genetic Algorithm. In: Proceedings on International Conference on Signal Processing, pp. 1213–1216 (1998)
Haykin, S.: Neural Networks - A Comprehensive Foundation, 2nd edn. PHI (1994)
Rajasekaran, S., Pai, G.A.V.: Neural Networks, Fuzzy Logic, and Genetic Algorithms Synthesis and Applications. PHI (2008)
Han, J., Kamber, M.: Data Mining - Concepts and Technique. Elsevier (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Si, T., Hazra, S., Jana, N.D. (2012). Artificial Neural Network Training Using Differential Evolutionary Algorithm for Classification. In: Satapathy, S.C., Avadhani, P.S., Abraham, A. (eds) Proceedings of the International Conference on Information Systems Design and Intelligent Applications 2012 (INDIA 2012) held in Visakhapatnam, India, January 2012. Advances in Intelligent and Soft Computing, vol 132. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-27443-5_88
Download citation
DOI: https://doi.org/10.1007/978-3-642-27443-5_88
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-27442-8
Online ISBN: 978-3-642-27443-5
eBook Packages: EngineeringEngineering (R0)