Welcome to the InfoSci Platform
Reference Hub2
Methodological Research for Modular Neural Networks Based on “an Expert With Other Capabilities”

Methodological Research for Modular Neural Networks Based on “an Expert With Other Capabilities”

Pan Wang, Jiasen Wang, Jian Zhang
Copyright: © 2018 |Volume: 26 |Issue: 2 |Pages: 23
ISSN: 1062-7375|EISSN: 1533-7995|EISBN13: 9781522542179|DOI: 10.4018/JGIM.2018040105
Cite Article Cite Article

MLA

Wang, Pan, et al. "Methodological Research for Modular Neural Networks Based on “an Expert With Other Capabilities”." JGIM vol.26, no.2 2018: pp.104-126. http://doi.org/10.4018/JGIM.2018040105

APA

Wang, P., Wang, J., & Zhang, J. (2018). Methodological Research for Modular Neural Networks Based on “an Expert With Other Capabilities”. Journal of Global Information Management (JGIM), 26(2), 104-126. http://doi.org/10.4018/JGIM.2018040105

Chicago

Wang, Pan, Jiasen Wang, and Jian Zhang. "Methodological Research for Modular Neural Networks Based on “an Expert With Other Capabilities”," Journal of Global Information Management (JGIM) 26, no.2: 104-126. http://doi.org/10.4018/JGIM.2018040105

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

This article contains a new subnet training method for modular neural networks, proposed with the inspiration of the principle of “an expert with other capabilities”. The key point of this method is that a subnet learns the neighbor data sets while fulfilling its main task: learning the objective data set. Additionally, a relative distance measure is proposed to replace the absolute distance measure used in the classical subnet learning method and its advantage in the general case is theoretically discussed. Both methodology and empirical study of this new method are presented. Two types of experiments respectively related with the approximation problem and the prediction problem in nonlinear dynamic systems are designed to verify the effectiveness of the proposed method. Compared with the classical subnet learning method, the average testing error of the proposed method is dramatically decreased and more stable. The superiority of the relative distance measure is also corroborated.

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.