Advertisement

Using Modular Neural Network with Artificial Bee Colony Algorithm for Classification

  • Wei-Xin Ling
  • Yun-Xia Wang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7928)

Abstract

The Artificial bee colony (ABC) algorithm has been used in several optimization problems, including the optimization of synaptic weights from an Artificial Neural Network (ANN). However, it is easy to trap in local minimum and not enough to generate a robust ANN. Modular neural networks (MNNs) are especially efficient for certain classes of regression and classification problems, as compared to the conventional monolithic artificial neural networks. In this paper, we present a model of MNN based on ABC algorithm (ABC-MNN). The experiments show that, compared to the monolithic ABCNN model, classifier designed in this model has higher training accuracy and generalization performance.

Keywords

Modular Neural Network Artificial Bee Colony Algorithm Learning Algorithm 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Karaboga, D.: An idea based on honey bee swarm for numerical optimization. Technical report, Computer Engineering Department, Engineering Faculty, Erciyes University (2005)Google Scholar
  2. 2.
    Karaboga, D., Basturk, B.: Artificial bee colony (ABC) optimization algorithm for solving constrained optimization problems. In: Melin, P., Castillo, O., Aguilar, L.T., Kacprzyk, J., Pedrycz, W. (eds.) IFSA 2007. LNCS (LNAI), vol. 4529, pp. 789–798. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  3. 3.
    Karaboga, D., Akay, B., Ozturk, C.: Artificial bee colony (ABC) optimization algorithm for training feed-forward neural networks. In: Torra, V., Narukawa, Y., Yoshida, Y. (eds.) MDAI 2007. LNCS (LNAI), vol. 4617, pp. 318–329. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  4. 4.
    Karaboga, D., Ozturk, C.: Neural networks training by artificial bee colony algorithm on pattern classification. Neural Network World 19(10), 279–292 (2009)Google Scholar
  5. 5.
    Karaboga, D., Ozturk, C., Akay, B.: Training neural networks with abc optimization algorithm on medical pattern classification. In: International Conference on Multivariate Statistical Modelling and High Dimensional Data Mining (2008)Google Scholar
  6. 6.
    Auda, G., Kamel, M.: Modualr Neural Network: A Survey. Int. Journal of Neural Systems 9(2), 129–151 (1999)CrossRefGoogle Scholar
  7. 7.
    Martinez, G., Melin, P., Castillo, O.: Optimization with Genetic Algorithms of Modular Neural Networks using Hierarichcal Genetic Algorithm Applied to Speech Recognition. In: Proceedings of International Joint Conference on Neural Networks, Canada (2005)Google Scholar
  8. 8.
    Hidalgo, D., Melin, P., Licea, G.: Optimization of modular neural networks with interval type-2 fuzzy logic integration using an evolutionary method with application to multimodal biometry. In: Melin, P., Kacprzyk, J., Pedrycz, W. (eds.) Bio-inspired Hybrid Intelligent Systems for Image Analysis and Pattern Recognition. SCI, vol. 256, pp. 111–121. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  9. 9.
    Sánchez, D., Melin, P., Castillo, O.: A New Model of Modular Neural Networks with Fuzzy Granularity for Pattern Recognition and Its Optimization with Hierarchical Genetic Algorithms. In: Batyrshin, I., Sidorov, G. (eds.) MICAI 2011, Part II. LNCS, vol. 7095, pp. 331–342. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  10. 10.
    Gori, M., Tesi, A.: On the problem of local minima in back propagation. IEEE Trans. Pattern Anal. Mach. Intell. 14(1), 76–86 (1992)CrossRefGoogle Scholar
  11. 11.
    Akay, B., Karaboga, D.: A modified Artificial Bee Colony algorithm for real-parameter optimization. Inform. Sci. (2010)Google Scholar
  12. 12.
    Ling, W.X., Zheng, Q.L., Chen, Q.: GPCMNN: A Parallel Cooperative Modular Neural Network Architecture Based On Gradient. Chinese Journal of Computers 27(9), 1256–1263 (2004)Google Scholar
  13. 13.
    Murphy, P.M., Aha, D.W.: UCI Repository of machine learning databases. Technical report, Irvine, CA, US (1994)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Wei-Xin Ling
    • 1
  • Yun-Xia Wang
    • 1
  1. 1.School of ScienceSouth China University of TechnologyGuangzhouChina

Personalised recommendations