Preprocessing of training set for back propagation algorithm: histogram equalization

Taek M. Kwon, Ehsan H. Feroz, Hui Cheng

Research output: Contribution to conferencePaperpeer-review

2 Scopus citations

Abstract

This paper introduces a data preprocessing algorithm that can improve the efficiency of the standard back propagation (BP) algorithm. The basic approach is transforming input data to a range that associates high-slopes of sigmoid where relatively large modification of weights occurs. This helps escaping of early trapping from prematured saturation. However, a simple and uniform transformation to such desired range can lead to a slow learning if the data have a heavily skewed distribution. In order to improve the performance of BP algorithm on such distribution, we propose a modified histogram equalization technique which enhances the spacing between data points in the heavily concentrated regions of skewed distribution. Our simulation study shows that this modified histogram equalization can significantly speed up the BP training as well as improving the generalization capability of the trained network.

Original languageEnglish (US)
Pages425-430
Number of pages6
StatePublished - Dec 1 1994
EventProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) - Orlando, FL, USA
Duration: Jun 27 1994Jun 29 1994

Other

OtherProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7)
CityOrlando, FL, USA
Period6/27/946/29/94

Fingerprint Dive into the research topics of 'Preprocessing of training set for back propagation algorithm: histogram equalization'. Together they form a unique fingerprint.

Cite this