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

See all articles by Taek M. Kwon

Taek M. Kwon

University of Minnesota - Twin Cities - Electrical and Computer Engineering

Ehsan H. Feroz

University of Washington, Milgard School of Business-Accounting ; University of Illinois at Urbana-Champaign; Government of the United States of America - US GAO Advisory Council; University of Minnesota, Labovitz School of Business-Department of Accounting; University of Minnesota, Carlson School of Management-Department of Accounting; American Accounting Association

Hui Pei Cheng

affiliation not provided to SSRN

Date Written: May 9, 2009

Abstract

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

Kwon, Taek M. and Feroz, Ehsan H. and Cheng, Hui Pei, Preprocessing of Training Set for Back Propagation Algorithm: Histogram Equalization (May 9, 2009). 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, Available at SSRN: https://ssrn.com/abstract=1401918

Taek M. Kwon

University of Minnesota - Twin Cities - Electrical and Computer Engineering ( email )

Duluth, MN 55812
United States

Ehsan H. Feroz (Contact Author)

University of Washington, Milgard School of Business-Accounting ( email )

1900 Commerce Street, Campus Box 358420
Tacoma, WA 98402-3100
United States
(253) 692 4728 (Phone)
253 692 4523 (Fax)

HOME PAGE: http://www.tacoma.washington.edu/business

University of Illinois at Urbana-Champaign ( email )

515 East Gregory Drive# 2307
Champaign, IL 61820
United States

Government of the United States of America - US GAO Advisory Council ( email )

441 G Street NW
Washington, DC 20548-0001
United States

University of Minnesota, Labovitz School of Business-Department of Accounting ( email )

10 University Drive
Labovitz School of Business
Duluth, MN 55812
United States
218-726-6988 (Phone)
218-726-8510 (Fax)

University of Minnesota, Carlson School of Management-Department of Accounting ( email )

420 Delaware St. SE
Minneapolis, MN 55455
United States

American Accounting Association ( email )

5717 Bessie Drive
Sarasota, FL 34233-2399
United States

Hui Pei Cheng

affiliation not provided to SSRN

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
54
Abstract Views
772
rank
412,193
PlumX Metrics