Optimizing Functional Link Neural Network Learning Using Modified Bee Colony on Multi-class Classifications
Functional Link Neural Network (FLNN) has emerged as an important tool for solving classification problems and widely applied in many engineering and scientific problems. FLNN is known to be conveniently used as compared to ordinary feed forward network like the Multilayer Perceptron (MLP) due to its flat network architecture which employs less tuneable weights. The standard method for tuning the weight in FLNN is using a Backpropagation (BP) learning algorithm. However, BP-learning algorithm has difficulties such as trapping in local minima and slow convergence especially for solving non-linearly separable classification problems. In this work, a modified Artificial Bee Colony (mABC) is used to recover the BP drawbacks. With modifications on the employed bee’s exploitation phase, the implementation of the mABC as a learning scheme for FLNN is expected to give a better accuracy result for the classification tasks.
KeywordsClassification Functional Link Neural Network Artificial Bee Colony Algorithm
Unable to display preview. Download preview PDF.
- 6.Karaboga, D.: An Idea Based on Honey Bee Swarm for Numerical Optimization. Erciyes University, Engineering Faculty, Computer Science Department, Kayseri/Turkiye (2005)Google Scholar
- 7.Pao, Y.H.: Adaptive pattern recognition and neural networks (1989)Google Scholar
- 9.Liu, L.M., Manry, M.T., Amar, F., Dawson, M.S., Fung, A.K.: Image classification in remote sensing using functional link neural networks. In: Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation (1994)Google Scholar
- 11.Klaseen, M., Pao, Y.H.: The functional link net in structural pattern recognition. In: 1990 IEEE Region 10 Conference on Computer and Communication Systems, TENCON 1990 (1990)Google Scholar
- 13.Majhi, R., Panda, G., Sahoo, G.: Development and performance evaluation of FLANN based model for forecasting of stock markets. Expert Systems with Applications 36(3, Part 2), 6800–6808 (2009)Google Scholar
- 16.Mohmad Hassim, Y.M., Ghazali, R.: Using Artificial Bee Colony to Improve Functional Link Neural Network Training. Applied Mechanics and Materials 263, 2102–2108 (2013)Google Scholar
- 17.Mohmad Hassim, Y.M., Ghazali, R.: Training a Functional Link Neural Network Using an Artificial Bee Colony for Solving a Classification Problems. Journal of Computing Press 4(9), 110–115 (2012)Google Scholar
- 18.Frank, A., Asuncion, A.: UCI Machine Learning Repository, School of Information and Computer Science, Irvine, CA. University of California (2010), http://archive.ics.uci.edu/ml