Fast convergence of error backpropagation algorithm through fuzzy modeling

R. J. Kuo, Y. T. Chen, P. H. Cohen, Soundar Rajan Tirupatikumara

Research output: Contribution to conferencePaper

7 Scopus citations

Abstract

Artificial neural networks (ANNs) have been widely used in many practical applications. Due to slow convergence of these networks, some changes have been reported in the literature in order to overcome these shortcomings. In this paper an intelligent ANN (IANN) which consists of the standard ANN and fuzzy modeling is proposed. The fuzzy modeling, which is able to dynamically adjust the standard ANN parameters including learning rate, momentum, and steepness of activation function, is employed to speed up the learning speed. The proposed IANN is developed and implemented in C language. Simulation results demonstrate that IANN is able to significantly speed up convergence and is more suitable than the standard ANN for many practical applications.

Original languageEnglish (US)
Pages239-244
Number of pages6
StatePublished - Dec 1 1993
EventProceedings of the 1993 Artificial Neural Networks in Engineering, ANNIE'93 - St.Louis, MO, USA
Duration: Nov 14 1993Nov 17 1993

Other

OtherProceedings of the 1993 Artificial Neural Networks in Engineering, ANNIE'93
CitySt.Louis, MO, USA
Period11/14/9311/17/93

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Software

Cite this

Kuo, R. J., Chen, Y. T., Cohen, P. H., & Tirupatikumara, S. R. (1993). Fast convergence of error backpropagation algorithm through fuzzy modeling. 239-244. Paper presented at Proceedings of the 1993 Artificial Neural Networks in Engineering, ANNIE'93, St.Louis, MO, USA, .