Teaching Learning Based Optimization for Neural Networks Learning Enhancement
Evolutionary computation is a collection of algorithms based on the evolution of a population towards a solution of certain problem. These algorithms can be used successfully in many applications requiring the optimization. These algorithms have been widely used to optimize the learning mechanism of classifiers, particularly on Artificial Neural Network (ANN) Classifier. Major disadvantages of ANN classifier are due to its slow convergence and always being trapped at the local minima. To overcome this problem, TLBO (Teaching learning based optimization) has been used to determine optimal value for learning mechanism. In this study, TLBO is chosen and applied to feed forward neural network to enhance the learning process. Two programs have developed, Differential Evolution Neural Network (DENN) and Particle Swarm Optimization with Neural Network (PSONN) to probe the impact of these methods on a Teaching learning based optimization with neural network (TLBONN) learning using various datasets. The results have revealed that TLBONN has given quite promising results in terms of smaller errors compared to PSONN and DENN.
KeywordsEvolutionary computation Swarm Optimization Artificial Neural Network
Unable to display preview. Download preview PDF.
- 5.Krishnanand, K.R., Panigrahi, B.K., Rout, P.K., Mohapatra, A.: Application of Multi-Objective Teaching-Learning-Based Algorithm to an Economic Load Dispatch Problem with Incommensurable Objectives. In: Panigrahi, B.K., Suganthan, P.N., Das, S., Satapathy, S.C. (eds.) SEMCCO 2011, Part I. LNCS, vol. 7076, pp. 697–705. Springer, Heidelberg (2011)CrossRefGoogle Scholar
- 7.Satapathy, S.C., Naik, A., Parvathi, K.: High dimensional real parameter optimization with teaching learning based optimization. International Journal of Industrial Engineering Computations (2012), doi:10.5267/j.ijiec.2012.06.001Google Scholar
- 9.Satapathy, S.C., Naik, A., Parvathi, K.: 0-1 Integer Programming for Generation Maintenance Scheduling in Power Systems Based on Teaching Learning Based Optimization (TLBO). In: Parashar, M., Kaushik, D., Rana, O.F., Samtaney, R., Yang, Y., Zomaya, A. (eds.) IC3 2012. CCIS, vol. 306, pp. 53–63. Springer, Heidelberg (2012)CrossRefGoogle Scholar
- 10.Naik, A., Satapathy, S.C., Parvathi, K.: Improvement of initial cluster center of c-means using Teaching learning based optimization, Accepted and will be published in Procedia Technology, Elsevier and indexed by ScopusGoogle Scholar
- 11.Naik, A., Satapathy, S.C.: Rough set and Teaching learning based optimization technique for Optimal Features Selection. Ref.: Ms. No. CEJCS-D-12-00042, under minor review in Central European Journal of Computer ScienceGoogle Scholar
- 13.Shamsuddin, S.M.: Number of Hidden Neurons, Universiti Teknologi Malaysia. Lecture Note Advanced Artificial Intelligence (2004)Google Scholar
- 14.Charytoniuk, W., Chen, M.S.: Neural Network Design for Short-term Load Forecasting. In: International Conference on Electric Utility Deregulation and Restructuring and Power Technologies 2000, City University, London, April 4-7, pp. 554–561 (2000)Google Scholar