Modification of Feed Forward Process and Activation Function in Back-Propagation

  • Gwang-Jun Kim
  • Dae-Hyon Kim
  • Yong-Kab Kim
Part of the Communications in Computer and Information Science book series (CCIS, volume 263)


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.


Backpropagation Normalization Feed-forward Process Sigmoid Activation Function Machine Vision 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kim, D.: Normalization Methods for Input and Output Vectors in Back propagation Neural Networks. International Journal of Computer Mathematics 71(2), 161–171 (1999)MathSciNetCrossRefzbMATHGoogle Scholar
  2. 2.
    Haykin, S.: Neural networks: a comprehensive foundation. Macmillan, New York, Maxwell Macmillan Canada, Toronto, Maxwell Macmillan International, New York (1994) Google Scholar
  3. 3.
    Fahlman, S.E.: An empirical study of learning speed in back propagation networks. Technical ReportCMU-CS-88-162, Carnegie Mellon University (1988) Google Scholar
  4. 4.
    Kim, D.: Standard and Advanced Back propagation models for image processing application in traffic engineering. ITS Journal 7(3-4), 199–211 (2002)zbMATHGoogle Scholar
  5. 5.
    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)Google Scholar
  6. 6.
    Kim, D.: Prediction Performance of Support Vector Machines on Input Vector Normaliza-tion Methods. International Journal of Computer Mathematics 81(5), 547–554 (2004)CrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Gwang-Jun Kim
    • 1
  • Dae-Hyon Kim
    • 1
  • Yong-Kab Kim
    • 2
  1. 1.Department of Computer EngineeringChonnam National UniversityYeosuKorea
  2. 2.School of Electrical Information EngineeringWonkwang UniversityIksanKorea

Personalised recommendations