Weak and strong convergence analysis of Elman neural networks via weight decay regularization

In this paper, we propose a novel variant of the algorithm to improve the generalization performance for Elman neural networks (ENN). Here, the weight decay term, also called regularization, which can effectively control the value of weights excessive growth, also over-fitting phenomenon can be effe...

Full description

Saved in:
Bibliographic Details
Published inOptimization Vol. 72; no. 9; pp. 2287 - 2309
Main Authors Zhou, Li, Fan, Qinwei, Huang, Xiaodi, Liu, Yan
Format Journal Article
LanguageEnglish
Published Philadelphia Taylor & Francis 02.09.2023
Taylor & Francis LLC
Subjects
Algorithms
Convergence
Decay
Elman neural networks
gradient method
Neural networks
Regularization
Online AccessGet full text

Cover

More Information
Summary:In this paper, we propose a novel variant of the algorithm to improve the generalization performance for Elman neural networks (ENN). Here, the weight decay term, also called regularization, which can effectively control the value of weights excessive growth, also over-fitting phenomenon can be effectively prevented. The main contribution of this work lies in that we have conducted a rigorous theoretical analysis of the proposed approach, i.e. the weak and strong convergence results are obtained. The comparison experiments to the problems of function approximation and classification on the real-world data have been performed to verify the theoretical results.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0233-1934
1029-4945
DOI:10.1080/02331934.2022.2057852