Artificial Bee Colony Training of Neural Networks
The Artificial Bee Colony (ABC) is a recently introduced swarm intelligence algorithm for optimization, that has previously been applied successfully to the training of neural networks. This paper explores more carefully the performance of the ABC algorithm for optimizing the connection weights of feed-forward neural networks for classification tasks, and presents a more rigorous comparison with the traditional Back-Propagation (BP) training algorithm. The empirical results show that using the standard “stopping early” approach with optimized learning parameters leads to improved BP performance over the previous comparative study, and that a simple variation of the ABC approach provides improved ABC performance too. With both improvements applied, we conclude that the ABC approach does perform very well on small problems, but the generalization performances achieved are only significantly better than standard BP on one out of six datasets, and the training times increase rapidly as the size of the problem grows.
KeywordsHide Unit Generalization Performance Training Neural Network Swarm Intelligence Algorithm Particle Swarm Optimiza
Unable to display preview. Download preview PDF.
- 1.Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)Google Scholar
- 2.Blake, C.L., Merz, C.J.: UCI Repository of Machine Learning Databases. University of California (1998), http://www.ics.uci.edu/~mlearn/MLRepository.html
- 5.Duch, W., Maszczyk, T., Jankowski, N.: Make it cheap: learning with O(nd) complexity. In: Proceedings of the World Congress on Computational Intelligence, pp. 132–135 (2012)Google Scholar
- 6.Engelbrecht, A.P.: Computational Intelligence: An Introduction. Wiley, Sussex (2007)Google Scholar
- 7.Karaboga, D.: An idea based on honey bee swarm for numerical optimization. Technical Report TR06, Computer Engineering Department, Erciyes University, Turkey (2005)Google Scholar
- 11.Karaboga, D., Ozturk, C.: Neural networks training by Artificial Bee Colony algorithm on pattern classification. Neural Network World 19, 279–292 (2009)Google Scholar
- 12.Ozturk, C., Karaboga, D.: Hybrid Artificial Bee Colony algorithm for neural network training. In: Proceedings of the IEEE Congress on Evolutionary Computation, pp. 84–88 (2011)Google Scholar
- 13.Prechelt, L.: PROBEN1 – A set of benchmarks and benchmarking rules for neural network training algorithms. Technical Report 21/94, Universitat Karlsruhe, Fakult at fur Informatik, Germany (1994)Google Scholar
- 14.Qiongshuai, L., Shiqing, W.: A hybrid model of neural network and classification in wine. In: Proceedings of the 3rd International Conference on Computer Research and Development, pp. 58–61 (2011)Google Scholar