Abstract
The back propagation algorithm calculates the weight changes of artificial neural networks, and a common approach is to use a training algorithm consisting of a learning rate and a momentum factor. The major drawbacks of above learning algorithm are the problems of local minima and slow convergence speeds. The addition of an extra term, called a proportional factor reduces the convergence of the back propagation algorithm. We have applied the three term back propagation to multiplicative neural network learning. The algorithm is tested on XOR and parity problem and compared with the standard back propagation training algorithm.
This is a preview of subscription content, log in via an institution to check access.
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
Zweiri, Y.H., Whidborne, J.F., Althoefer, K., Seneviratne, L.D.: A three term back propagation algorithm. Neurocomputing 50, 305–318 (2003)
Edward, R.J.: An Introduction to Neural Networks. In: A White paper. Visual Numerics Inc., United States of America (2004)
Yam, Y.F., Chow, T.W.S.: Extended back propagation algorithm. Electronics Letters 29(19), 1701–1702 (1993)
Verma, B.K., Mulawka, J.J.: A modified back propagation algorithm. In: IEEE World Congress on Computational Intelligence, pp. 840–844 (1994)
Drago, G.P., Morando, M., Ridella, S.: An adaptive momentum back propagation. Neural Computing and Application 3, 213–221 (1995)
Chen, Y.Q., Yin, T., Babri, H.A.: A stochastic back propagation algorithm for training neural networks. In: International Conference on Information, Communications and Signal Processing, Singapore, pp. 703–707 (1997)
Ng, S.C., Leung, S.H., Luk, A.: Fast convergent generalized back propagation algorithm with constant learning rate. Neural Processing Letters 9, 13–23 (1999)
Wen, J.W., Zhao, J.L., Luo, S.W., Han, Z.: The improvements of BP neural network learning algorithm. In: ICSP 2000, pp. 1647–1649 (2000)
Wang, X.G., Tang, Z., Tamura, H., Ishii, M., Sun, W.D.: An improved back propagation algorithm to avoid the local minima problem. Neuro Computing 56, 455–460 (2004)
Wang, C.H., Kao, C.H., Lee, W.H.: A new interactive model for improving the learning performance of back propagation neural network. Automation in Construction 16(6), 745–758 (2007)
Bayati, A.Y.A., Sulaiman, N.A., Sadiq, G.W.: A modified conjugate radient formula for back propagation Neural Network Algorithm. Journal of Computer Science 5(11), 849–856 (2009)
Mel, B.: Information processing in dendritic trees. Neural Computing 6, 1031–1085 (1994)
Yadav, R.N., Kalra, P.K., John, J.: Time series prediction with single multiplicative neuron model. Applied Soft Computing 7, 1157–1163 (2007)
Yadav, R.N., Singh, V., Kalra, P.K.: Classification using single neuron. In: IEEE Int. Conf. on Industrial Informatics, Banff, Alberta, Canada, pp. 124–129 (2003)
Yu, C.C., Liu, B.D.: A back propagation algorithm with adaptive learning rate and momentum coefficient. In: The International Joint Conference on Neural Networks, IJCNN 2002, pp. 1218–1223 (2007)
Zweiri, Y.H.: Optimization of a Three-Term Backpropagation Algorithm Used for Neural Network Learning. International Journal of Engineering and Mathematical Sciences 3(4), 322–327 (2007)
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
Burse, K., Manoria, M., Kirar, V.P.S. (2011). Improved Back Propagation Algorithm to Avoid Local Minima in Multiplicative Neuron Model. In: Das, V.V., Thomas, G., Lumban Gaol, F. (eds) Information Technology and Mobile Communication. AIM 2011. Communications in Computer and Information Science, vol 147. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-20573-6_11
Download citation
DOI: https://doi.org/10.1007/978-3-642-20573-6_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-20572-9
Online ISBN: 978-3-642-20573-6
eBook Packages: Computer ScienceComputer Science (R0)