Welcome to the InfoSci Platform
Development of the Enhanced Piece-Wise Linear Neural Network Algorithm

Development of the Enhanced Piece-Wise Linear Neural Network Algorithm

Veronica K. Chan, Christine W. Chan
Copyright: © 2020 |Pages: 23
ISBN13: 9781799830382|ISBN10: 1799830381|ISBN13 Softcover: 9781799830399|EISBN13: 9781799830405
DOI: 10.4018/978-1-7998-3038-2.ch006
Cite Chapter Cite Chapter

MLA

Chan, Veronica K., and Christine W. Chan. "Development of the Enhanced Piece-Wise Linear Neural Network Algorithm." Innovations, Algorithms, and Applications in Cognitive Informatics and Natural Intelligence, edited by Kwok Tai Chui, et al., IGI Global, 2020, pp. 104-126. https://doi.org/10.4018/978-1-7998-3038-2.ch006

APA

Chan, V. K. & Chan, C. W. (2020). Development of the Enhanced Piece-Wise Linear Neural Network Algorithm. In K. Chui, M. Lytras, R. Liu, & M. Zhao (Eds.), Innovations, Algorithms, and Applications in Cognitive Informatics and Natural Intelligence (pp. 104-126). IGI Global. https://doi.org/10.4018/978-1-7998-3038-2.ch006

Chicago

Chan, Veronica K., and Christine W. Chan. "Development of the Enhanced Piece-Wise Linear Neural Network Algorithm." In Innovations, Algorithms, and Applications in Cognitive Informatics and Natural Intelligence, edited by Kwok Tai Chui, et al., 104-126. Hershey, PA: IGI Global, 2020. https://doi.org/10.4018/978-1-7998-3038-2.ch006

Export Reference

Mendeley
Favorite

Abstract

This chapter discusses development, application, and enhancement of a decomposition neural network rule extraction algorithm for nonlinear regression problems. The dual objectives of developing the algorithms are (1) to generate good predictive models comparable in performance to the original artificial neural network (ANN) models and (2) to “open up” the black box of a neural network model and provide explicit information in the form of rules that are expressed as linear equations. The enhanced PWL-ANN algorithm improves upon the PWL-ANN algorithm because it can locate more than two breakpoints and better approximate the hidden sigmoid activation functions of the ANN. Comparison of the results produced by the two versions of the PWL-ANN algorithm showed that the enhanced PWL-ANN models provide higher predictive accuracies and improved fidelities compared to the originally trained ANN models than the PWL-ANN models.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.