Abstract
Recently, evolutionary neural networks are hot topics in a neural network community because of their flexibility and good performance. However, they suffer from a premature convergence problem caused by the genetic drift of evolutionary algorithms. The genetic diversity in a population decreases quickly and it loses an exploration capability. Based on the inspiration of diversity in nature, a number of speciation algorithms are proposed to maintain diverse solutions from the population. One problem arising from this approach is lack of information on the distance measures among neural networks to penalize or discard similar solutions. In this paper, a comparison is conducted for six distance measures (genotypic, phenotypic, and behavioral types) with representative speciation algorithms (fitness sharing and deterministic crowding genetic algorithms) on six UCI benchmark datasets. It shows that the choice of distance measures is important in the neural network evolution.
This is a preview of subscription content, log in via an institution to check access.
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
Yao, X., Islam, M.M.: Evolving artificial neural network ensembles. IEEE Computational Intelligence Magazine (2008)
Baeck, T., Fogel, D.B., Michalewicz, Z.: Advanced algorithms and operations (Evolutionary Computation). Taylor & Francis, London (2000)
Hwang, K.-S., Cho, S.-B.: Improving evolvable hardware by applying the speciation technique. Applied Soft Computing 9(1), 254–263 (2008)
Hong, J.-H., Cho, S.-B.: Efficient huge-scale feature selection with speciated genetic algorithm. Pattern Recognition Letters 27(2), 143–150 (2006)
Ahn, J.-H., Cho, S.-B.: Speciated neural networks evolved with fitness sharing technique. In: Proceedings of the 2001 Congress on Evolutionary Computation, pp. 390–396 (2001)
Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation 10(2), 99–127 (2002)
Jung, S.-C., Moon, B.-R.: Central point crossover for neuro-genetic hybrids. In: Deb, K., et al. (eds.) GECCO 2004. LNCS, vol. 3102, pp. 1292–1303. Springer, Heidelberg (2004)
Sallam, H., Regazzoni, C.S., Talkhan, I., Atiya, A.: Measuring the genotype diversity of evolvable neural networks. In: Proceedings of the 6th International Conference on Informatics and Systems, pp. 38–43 (2008)
Sallam, H., Regazzoni, C.S., Talkhan, I., Atiya, A.: Evolving neural networks ensembles NNEs. In: 2008 IAPR Workshop on Cognitive Information Processing, pp. 142–147 (2008)
Ormoneit, D.: A regularization approach to continuous learning with an application to financial derivatives pricing. Neural Networks (12), 1405–1412 (1999)
Li, K., Huang, H.-K., Ye, X.-C., Cui, L.-J.: A selective approach to neural network ensemble based on clustering technology. In: Proceedings of the Third International Conference on Machine Learning and Cybernetics, pp. 3229–3233 (2004)
Khare, V., Yao, X.: Artificial speciation of neural network ensembles. In: Proceedings of the 2002 UK Workshop on Computational Intelligence, pp. 96–103 (2002)
Trujillo, L., Olague, G., Lutton, E., de Vega, F.F.: Discovering several robot behaviors through speciation. In: Giacobini, M., Brabazon, A., Cagnoni, S., Di Caro, G.A., Drechsler, R., Ekárt, A., Esparcia-Alcázar, A.I., Farooq, M., Fink, A., McCormack, J., O’Neill, M., Romero, J., Rothlauf, F., Squillero, G., Uyar, A.Ş., Yang, S. (eds.) EvoWorkshops 2008. LNCS, vol. 4974, pp. 164–174. Springer, Heidelberg (2008)
Cioppa, A.D., Stefano, C.D., Marcelli, A.: On the role of population size and niche radius in fitness sharing. IEEE Transactions on Evolutionary Computation 8(6), 580–592 (2004)
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
Kim, KJ., Cho, SB. (2009). Evaluation of Distance Measures for Speciated Evolutionary Neural Networks in Pattern Classification Problems. In: Leung, C.S., Lee, M., Chan, J.H. (eds) Neural Information Processing. ICONIP 2009. Lecture Notes in Computer Science, vol 5864. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-10684-2_70
Download citation
DOI: https://doi.org/10.1007/978-3-642-10684-2_70
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-10682-8
Online ISBN: 978-3-642-10684-2
eBook Packages: Computer ScienceComputer Science (R0)