A Modified Artificial Bee Colony Optimization for Functional Link Neural Network Training
Functional Link Neural Network (FLNN) has becoming as an important tool for solving non-linear classification problem. This is due to its modest architecture which required less tunable weights for learning as compared to the standard multilayer feed forward network. The most common learning scheme for tuning the weight in FLNN is a Backpropagation (BP-learning) algorithm. However, the learning method by BP-learning algorithm tends to easily get trapped in local minima which affect the performance of FLNN. This paper discussed the implementation of modified Artificial Bee Colony (mABC) as a learning scheme for training the FLNN network in overcoming the drawback of BP-learning scheme. The aim is to introduce an alternative learning scheme that can provide a better solution for training the FLNN network.
KeywordsFunctional link neural network Modified artificial bee colony Learning scheme Training
Unable to display preview. Download preview PDF.
The authors wish to thank the Ministry of Higher Education Malaysia and Universiti Tun Hussein Onn Malaysia for the scholarship given in conducting these research activities.
- 1.Zhang, G.P., Neural networks for classification: a survey. Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on, 2000. 30(4): p. 451-462.Google Scholar
- 2.Liao, S.-H. and Wen, C.-H., Artificial neural networks classification and clustering of methodologies and applications – literature analysis from 1995 to 2005. Expert Systems with Applications, 2007. 32(1): p. 1-11.Google Scholar
- 3.Pao, Y.H. and Takefuji, Y., Functional-link net computing: theory, system architecture, and functionalities. Computer, 1992. 25(5): p. 76-79.Google Scholar
- 4.Dehuri, S. and Cho, S.-B., A comprehensive survey on functional link neural networks and an adaptive PSO–BP learning for CFLNN. Neural Computing & Applications 2010. 19(2): p. 187-205.Google Scholar
- 5.Mohmad Hassim, Y.M. and Ghazali, R., Using Artificial Bee Colony to Improve Functional Link Neural Network Training. Applied Mechanics and Materials, 2013. 263: p. 2102-2108.Google Scholar
- 6.Karaboga, D., An Idea Based on Honey Bee Swarm for Numerical Optimization. 2005, Erciyes University, Engineering Faculty, Computer Science Department, Kayseri/Turkiye.Google Scholar
- 7.Karaboga, D. and Basturk, B., On the performance of artificial bee colony (ABC) algorithm. Elsevier Applied Soft Computing, 2007. 8: p. 687-697.Google Scholar
- 8.Pao, Y.-H., Adaptive pattern recognition and neural networks. 1989: Addison-Wesley Longman Publishing Co., Inc. 309.Google Scholar
- 9.Misra, B.B. and Dehuri, S., Functional Link Artificial Neural Network for Classification Task in Data Mining. Journal of Computer Science, 2007. 3(12): p. 948-955.Google Scholar
- 10.Haring, S. and Kok, J. Finding functional links for neural networks by evolutionary computation. in In: Van de Merckt Tet al (eds) BENELEARN1995, proceedings of the fifth Belgian–Dutch conference on machine learning. 1995. Brussels, Belgium: pp 71–78.Google Scholar
- 11.Haring, S., Kok, J., and Van Wesel, M., Feature selection for neural networks through functional links found by evolutionary computation. In: ILiu X et al (eds) Adavnces in intelligent data analysis (IDA-97). LNCS 1280, 1997: p. 199–210.Google Scholar
- 12.Abu-Mahfouz, I.-A., A comparative study of three artificial neural networks for the detection and classification of gear faults International Journal of General Systems 2005. 34(3): p. 261-277.Google Scholar
- 13.Sierra, A., Macias, J.A., and Corbacho, F., Evolution of functional link networks. Evolutionary Computation, IEEE Transactions on, 2001. 5(1): p. 54-65.Google Scholar
- 14.Dehuri, S., Mishra, B.B., and Cho, S.-B., Genetic Feature Selection for Optimal Functional Link Artificial Neural Network in Classification, in Proceedings of the 9th International Conference on Intelligent Data Engineering and Automated Learning. 2008, Springer-Verlag: Daejeon, South Korea. p. 156-163.Google Scholar
- 15.Ghazali, R., Hussain, A.J., and Liatsis, P., Dynamic Ridge Polynomial Neural Network: Forecasting the univariate non-stationary and stationary trading signals. Expert Systems with Applications, 2011. 38(4): p. 3765-3776.Google Scholar
- 16.Mohmad Hassim, Y.M. and Ghazali, R., Training a Functional Link Neural Network Using an Artificial Bee Colony for Solving a Classification Problems. Journal of Computing Press, NY, USA, 2012. 4(9): p. 110-115.Google Scholar