Modification of Feed Forward Process and Activation Function in Back-Propagation
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.
KeywordsBackpropagation Normalization Feed-forward Process Sigmoid Activation Function Machine Vision
Unable to display preview. Download preview PDF.
- 2.Haykin, S.: Neural networks: a comprehensive foundation. Macmillan, New York, Maxwell Macmillan Canada, Toronto, Maxwell Macmillan International, New York (1994) Google Scholar
- 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
- 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