Abstract
This paper suggests an approach to neural network training through the simultaneous optimization of architectures and weights with a Particle Swarm Optimization (PSO)-based multiobjective algorithm. Most evolutionary computation-based training methods formulate the problem in a single objective manner by taking a weighted sum of the objectives from which a single neural network model is generated. Our goal is to determine whether Multiobjective Particle Swarm Optimization can train neural networks involving two objectives: accuracy and complexity. We propose rules for automatic deletion of unnecessary nodes from the network based on the following idea: a connection is pruned if its weight is less than the value of the smallest bias of the entire network. Experiments performed on benchmark datasets obtained from the UCI machine learning repository show that this approach provides an effective means for training neural networks that is competitive with other evolutionary computation-based methods.
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
Abbass, H.: An Evolutionary Artificial Neural Networks Approach to Breast Cancer Diagnosis. Artificial Intelligence in Medicine 25(3), 265–281 (2002)
Alfassio Grimaldi, E., Grimaccia, F., Mussetta, M., Zich, R.: PSO as an Effective Learning Algorithm for Neural Network Applications. In: Proceedings of the International Conference on Computational Electromagnetics and its Applications, Beijing - China, pp. 557–560 (2004)
Al-kazemi, B., Mohan, C.: Training Feedforward Neural Networks using Multi-phase Particle Swarm Optimization. In: Proceedings of the 9th International Conference on Neural Information Processing (ICONIP 2002), Singapore (2002)
Barron, A., Rissanen, J., Yu, B.: The Minimum Description Length Principle in Coding and Modeling. IEEE Trans. Inform. Theory 44, 2743–2760 (1998)
Coello, C., Lechuga, M.: MOPSO: A Proposal for Multiple Objective Particle Swarm Optimization. In: Proceedings of the IEEE Congress on Evolutionary Computation (CEC 2002), Honolulu, Hawaii USA (2002)
Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.: A Fast and Elitist Multiobjective Genetic Algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation 6(2), 182–197 (2002)
Fieldsend, J.: Multi-Objective Particle Swarm Optimisation Methods. Technical Report # 419, Department of Computer Science, University of Exeter (2004)
Grunwald, P.: A Tutorial Introduction to the Minimum Description Length Principle. Advances in Minimum Description Length: Theory and Applications. MIT Press, Cambridge (2004)
Gudise, V., Venayagamoorthy, G.: Comparison of Particle Swarm Optimization and Backpropagation as Training Algorithms for Neural Networks. In: IEEE Swarm Intelligence Symposium, Indianapolis, IN, USA, pp. 110–117 (2003)
Hinton, G., van Camp, D.: Keeping Neural Networks Simple by Minimizing the Description Length of the Weights. In: Proceedings of COLT 1993 (1993)
Jin, Y., Sendhoff, B., Körner, E.: Evolutionary Multi-objective Optimization for Simultaneous Generation of Signal-type and Symbol-type Representations. In: Coello Coello, C.A., Hernández Aguirre, A., Zitzler, E. (eds.) EMO 2005. LNCS, vol. 3410, pp. 752–766. Springer, Heidelberg (2005)
Kennedy, J., Eberhart, R.: Particle Swarm Optimization. In: Proceedings of the 1995 IEEE International Conference on Neural Networks, Perth, Australia, vol. 4, pp. 1942–1948 (1995)
Liu, Y., Yao, X.: A Population-Based Learning Algorithm Which Learns Both Architectures and Weights of Neural Networks. Chinese J. Advanced Software Res. 3(1), 54–65 (1996)
Newman, D., Hettich, S., Blake, C., Merz, C.: UCI Repository of machine learning databases. University of California, Irvine, CA, Department of Information and Computer Science (1998)
Palmes, P., Hayasaka, T., Usui, S.: Mutation-based Genetic Neural Network. IEEE Transactions on Neural Networks 16(3), 587–600 (2005)
Raquel, C., Naval, P.: An Effective Use of Crowding Distance in Multiobjective Particle Swarm Optimization. In: Beyer, H. (ed.) Proceedings of the 2005 Conference on Genetic and Evolutionary Computation, GECCO 2005, Washington DC, USA, June 25-29, 2005, pp. 257–264. ACM Press, New York (2005)
Shahin, M., Jaksa, M., Maier, H.: Application of Neural Networks in Foundation Engineering. Theme paper to the International e-Conference on Modern Trends in Foundation Engineering: Geotechnical Challenges and Solutions, Theme No. 5: Numerical Modelling and Analysis, Chennai, India (2004)
Sugisaka, M., Fan, X.: An Effective Search Method for Neural Network Based Face Detection Using Particle Swarm Optimization. IEICE Transactions 88-D(2), 214–222 (2005)
van den Bergh, F.: Particle Swarm Weight Initialization in Multi-layer Perceptron Artificial Neural Networks. Development and Practice of Artificial Intelligence Techniques, Durban, South Africa, pp. 41–45 (1999)
Yao, X.: Evolving Artificial Neural Networks. Proceedings of the IEEE 87, 1423–1447 (1999)
Yao, X., Liu, Y.: Evolving Artificial Neural Networks through Evolutionary Programming. In: The Fifth Annual Conference on Evolutionary Programming, San Diego, CA, USA, February 29-March 2, pp. 257–266. MIT Press, Cambridge (1996)
Yao, X., Liu, Y.: Towards Designing Artificial Neural Networks by Evolution. Applied Mathematics and Computation 91(1), 83–90 (1998)
Zhao, F., Ren, Z., Yu, D., Yang, Y.: Application of An Improved Particle Swarm Optimization Algorithm for Neural Network Training. In: Proceedings of the 2005 International Conference on Neural Networks and Brain, Beijing, China, vol. 3, pp. 1693–1698 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yusiong, J.P.T., Naval, P.C. (2006). Training Neural Networks Using Multiobjective Particle Swarm Optimization. In: Jiao, L., Wang, L., Gao, Xb., Liu, J., Wu, F. (eds) Advances in Natural Computation. ICNC 2006. Lecture Notes in Computer Science, vol 4221. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11881070_116
Download citation
DOI: https://doi.org/10.1007/11881070_116
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-45901-9
Online ISBN: 978-3-540-45902-6
eBook Packages: Computer ScienceComputer Science (R0)