Abstract
One of the introduce discussions in the field of using MLPNN, as a tools for data classification is related to the error back propagation algorithm which use to train the network. It has challenges for large-scale and heterogeneous data such as, lack of memory and low–speed convergence, besides, computational load is high. In this paper proposed method with partial and random updating some of weights instead of all of them in each iteration, cause to decrease computational rate, improve lack of memory’s problem and somewhat increase convergence speed. Result of experiments on two standard dataset, demonstrate efficiency of algorithm.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Didandeh, A., Mirbakhsh, N., Amiri, A., Fathy, M.: AVLR-EBP, A Variable Step Size Approach to Speed-up the Convergence of Error Back-Propagation Algorithm. Neural Processing Letters 3(2), 201–214 (2011)
Rahmani, N.M., Amiri, A., Fathy, M.: Partial Update Error Back Propagation Algorithm. In: Proceedings of the 15th Iranian Conference on Electrical Engineering, Tehran, Iran (2010)
Sarkar, D.: Methods to Speed Up Error Back-Propagation Learning Algorithm. ACM Computing Surveys 27(4), 545–644 (1995)
Wilamowski, M.B.: Advanced Learning Algorithms, February 17. IEEE (2010)
Rojas, R.: The Back propagation Algorithm. Neural Networks (1996)
Abid, S., Faniech, F., Jervis, B.W., Cheriet, M.: Fast training of multilayer perceptrons with a mixed norm algorithm. In: The IEEE Intl. Joint Conference on Neural Networks (IJCNN 2005), Canada, vol. 2, pp. 1018–1022 (August 2005)
Mulawka, J.J., Verma, B.K.: Improving the Training Time of the Backpropagation Algorithm. International Journal of Microcomputer Applications 13(2), 85–89 (1994)
Verma, B.: Fast training of multilayer perceptrons (MLPs). IEEE Trans. Neural Netw. 8(6), 1314–1321 (1997)
Haykin, S.: Neural Networks, a comprehensive foundation, 2nd edn. Prentice Hall International Inc., McMaster University, Hamilton, Ontario, Canada (1998)
Gamal-Eldin, A., Descombes, X., Charpiat, G., Zerubia, J.: Multiple Birth and Cut Algorithm for Multiple Object Detection. Journal of Multimedia Processing and Technologies 1(4), 261–277 (2010)
Chen, C., Tan, J., Zhang, F., Yao, J.: Quality Prediction Model Based on Variable-Learning-Rate Neural Networks in Tobacco Redrying Process. Journal of Intelligent Computing 1(3), 157–164 (2010)
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
Latifi, N., Amiri, A. (2011). Partial and Random Updating Weights in Error Back Propagation Algorithm. In: Pichappan, P., Ahmadi, H., Ariwa, E. (eds) Innovative Computing Technology. INCT 2011. Communications in Computer and Information Science, vol 241. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-27337-7_39
Download citation
DOI: https://doi.org/10.1007/978-3-642-27337-7_39
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-27336-0
Online ISBN: 978-3-642-27337-7
eBook Packages: Computer ScienceComputer Science (R0)