Abstract
In some practical NN applications, fast response to external events within enormously short time is highly demanded. However, by using back propagation (BP) based on gradient descent optimization method obviously not satisfy in several application due to serious problems associated with BP which are slow learning convergence velocity and confinement to shallow minima. Over the years, many improvements and modifications of the back propagation learning algorithm have been reported. In this research, we modified existing back propagation learning algorithm with adaptive gain by adaptively change the momentum coefficient and learning rate. In learning the patterns, the simulation results indicate that the proposed algorithm can hasten up the convergence behaviour as well as slide the network through shallow local minima compare to conventional BP algorithm. We use three common benchmark classification problems to illustrate the improvement of the proposed algorithm.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Haykin, S.: Neural Networks and Learning Machines. Prentice Hall, New Jersey (2009)
Nawi, N.M., Ransing, R.S., Salleh, M.N.M., Ghazali, R., Hamid, N.A.: An Improved Back Propagation Neural Network Algorithm on Classification Problems. In: Zhang, Y., Cuzzocrea, A., Ma, J., Chung, K.-i., Arslan, T., Song, X. (eds.) DTA and BSBT 2010. Communications in Computer and Information Science, vol. 118, pp. 177–188. Springer, Heidelberg (2010)
Nawi, N.M., Ghazali, R., Salleh, M.N.M.: The Development of Improved Back-Propagation Neural Networks Algorithm for Predicting Patients with Heart Disease. In: Zhu, R., Zhang, Y., Liu, B., Liu, C. (eds.) ICICA 2010. LNCS, vol. 6377, pp. 317–324. Springer, Heidelberg (2010)
Sabeti, V., Samavi, S., Mahdavi, M., Shirani, S.: Steganalysis and Payload Estimation of Embedding in Pixel Differences using Neural Networks. Pattern Recogn. 43, 405–415 (2010)
Mandal, S., Sivaprasad, P.V., Venugopal, S., Murthy, K.P.N.: Artificial Neural Network Modeling to Evaluate and Predict the Deformation Behavior of Stainless Steel Type AISI 304L during Hot Torsion. Applied Soft Computing 9, 237–244 (2009)
Subudhi, B., Morris, A.S.: Soft Computing Methods Applied to the Control of a Flexible Robot Manipulator. Applied Soft Computing 9, 149–158 (2009)
Lee, K., Booth, D., Alam, P.: A Comparison of Supervised and Unsupervised Neural Networks in Predicting Bankruptcy of Korean Firms. Expert Systems with Applications 29, 1–16 (2005)
Sharda, R., Delen, D.: Predicting Box-Office Success of Motion Pictures with Neural Networks. Expert Systems with Applications 30, 243–254 (2006)
Yu, L., Wang, S.-Y., Lai, K.K.: An Adaptive BP Algorithm with Optimal Learning Rates and Directional Error Correction for Foreign Exchange Market Trend Prediction. In: Wang, J., Yi, Z., Żurada, J.M., Lu, B.-L., Yin, H. (eds.) ISNN 2006. LNCS, vol. 3973, pp. 498–503. Springer, Heidelberg (2006)
Lera, G., Pinzolas, M.: Neighborhood Based Levenberg-Marquardt Algorithm for Neural Network Training. IEEE Transaction on Neural Networks 13, 1200–1203 (2002)
Wang, X.G., Tang, Z., Tamura, H., Ishii, M., Sun, W.D.: An Improved Backpropagation Algorithm to Avoid The Local Minima Problem. Neurocomputing 56, 455–460 (2004)
Otair, M.A., Salameh, W.A.: Speeding Up Back-Propagation Neural Networks. In: Proceedings of the 2005 Informing Science and IT Education Joint Conference. pp.167 173.Flagstaff, Arizona, USA (2005)
Ji, L., Wang, X., Yang, X., Liu, S., Wang, L.: Back-Propagation Network Improved by Conjugate Gradient Based on Genetic Algorithm in Qsar Study on Endocrine Disrupting Chemicals. Chinese Science Bulletin 53, 33–39 (2008)
Nawi, N.M., Ransing, R.S., Ransing, M.S.: An Improved Conjugate Gradient Based Learning Algorithm for Back Propagation Neural Networks. International Journal of Information and Mathematical Sciences 4, 46–55 (2008)
Evett, I.W., Spiehler, E.J.: Rule Induction in Forensic Science. Knowledge Based Systems, 152–160 (1988)
Michalski, R.S., Chilausky, R.L.: Learning by Being Told and Learning from Examples: An Experimental Comparison of the Two Methods of Knowledge Acquisition in the Context of Developing an Expert System for Soybean Disease Diagnosis. International Journal of Policy Analysis and Information Systems 4(2) (1980)
Mangasarian, O.L., Wolberg, W.H.: Cancer diagnosis via linear programming. SIAM News 23, 1–18 (1990)
Ye, Y.C.: Application and Practice of the Neural Networks. Scholars Publication, Taiwan (2001)
Maier, H.R., Dandy, G.C.: The Effect of Internal Parameters and Geometry on The Performance Of Back-Propagation Neural Networks: An Empirical Study. Environmental Modelling and Software 13, 193–209 (1998)
Thimm, G., Moerland, P., Fiesler, E.: The Interchangeability of Learning Rate and Gain in Backpropagation Neural Networks. Neural Comput. 8, 451–460 (1996)
Eom, K., Jung, K., Sirisena, H.: Performance Improvement of Backpropagation Algorithm by Automatic Activation Function Gain Tuning Using Fuzzy Logic. Neurocomputing 50, 439–460 (2003)
Hamid, N.A., Nawi, N.M., Ghazali, R.: The Effect of Adaptive Gain and Adaptive Momentum in Improving Training Time of Gradient Descent Back Propagation Algorithm on Classification Problems. In: Proceeding of the International Conference on Advanced Science, Engineering and Information Technology, Hotel Equatorial Bangi-Putrajaya, Malaysia , pp. 178–184 (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Abdul Hamid, N., Mohd Nawi, N., Ghazali, R., Mohd Salleh, M.N. (2011). Learning Efficiency Improvement of Back Propagation Algorithm by Adaptively Changing Gain Parameter together with Momentum and Learning Rate. In: Zain, J.M., Wan Mohd, W.M.b., El-Qawasmeh, E. (eds) Software Engineering and Computer Systems. ICSECS 2011. Communications in Computer and Information Science, vol 181. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-22203-0_68
Download citation
DOI: https://doi.org/10.1007/978-3-642-22203-0_68
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-22202-3
Online ISBN: 978-3-642-22203-0
eBook Packages: Computer ScienceComputer Science (R0)