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 L-2 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.

Automated summary

In this paper, a novel variant of the algorithm is proposed to improve the generalization performance for Elman neural networks. By controlling the weight growth and preventing over-fitting, rigorous theoretical analysis and experimental verification have been conducted.