Abstract
Research on neural networks has grown significantly over the past decade, with valuable contributions made from many different academic disciplines. While there are currently many different types of neural network models, Back-propagation is the most popular neural network model. However, the input vectors in the Back-propagation neural network model usually need to be normalized and the normalization methods affect the prediction accuracy. In this study, a new method is proposed in which an additional feed-forward process was included in the Back propagation model and a sigmoid activation function was modified, in order to overcome the input vector normalization problem. The experimental results showed that the proposed approach might produce a better training and prediction accuracy than the most current common approach using input vector normalization and that it has the potential to improve performance in machine vision applications.
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
Kim, D.: Normalization Methods for Input and Output Vectors in Back propagation Neural Networks. International Journal of Computer Mathematics 71(2), 161–171 (1999)
Haykin, S.: Neural networks: a comprehensive foundation. Macmillan, New York, Maxwell Macmillan Canada, Toronto, Maxwell Macmillan International, New York (1994)
Fahlman, S.E.: An empirical study of learning speed in back propagation networks. Technical ReportCMU-CS-88-162, Carnegie Mellon University (1988)
Kim, D.: Standard and Advanced Back propagation models for image processing application in traffic engineering. ITS Journal 7(3-4), 199–211 (2002)
Rumelhart, D.E., Hinton, G.E., McClelland, J.L.: A general framework for parallel distributed processing. In: Rumelhart, D.E., McClelland, J.L., The PDP Research Group (eds.) Parallel Distributed Processing, vol. 1&2, MIT Press, Cambridge (1986)
Kim, D.: Prediction Performance of Support Vector Machines on Input Vector Normaliza-tion Methods. International Journal of Computer Mathematics 81(5), 547–554 (2004)
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
Kim, GJ., Kim, DH., Kim, YK. (2011). Modification of Feed Forward Process and Activation Function in Back-Propagation. In: Kim, Th., et al. Multimedia, Computer Graphics and Broadcasting. MulGraB 2011. Communications in Computer and Information Science, vol 263. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-27186-1_30
Download citation
DOI: https://doi.org/10.1007/978-3-642-27186-1_30
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-27185-4
Online ISBN: 978-3-642-27186-1
eBook Packages: Computer ScienceComputer Science (R0)