Preprocessing of Training Set for Back Propagation Algorithm: Histogram Equalization
1994 IEEE International Conference on Neural Networks, IEEE World Congress on Computational Intelligence, Vol. 1, pp. 425-43, Orlando, FL, USA, June 27-June29, 1994
8 Pages Posted: 10 May 2009 Last revised: 15 Jun 2009
Date Written: May 9, 2009
This paper considered a preprocessing of input data to improve the performance of standardized BP learning algorithm. In general, even a simple uniform transformation into a proper range improves the efficiency of the BP algorithm. However, uniform transformation becomes inefficient if the input distribution is very skewed. To correct this problem, we propose a modified histogram equalization technique that converts the skewed and irregular distribution to a distribution favorable to the BP algorithm. Our simulation with the S&L failure classification data indicates that the proposed preprocessing leads to a better performance of the BP algorithm than a simple transformation or the conventional histogram equalization.
Keywords: Backpropagation, S&L, Banks, Failure Classification
JEL Classification: C45, G21
Suggested Citation: Suggested Citation