Discussion of stability in a class of models on recurrent wavelet neural networks

• Published in: Applied mathematics and mechanics Vol. 28; no. 4; pp. 471 - 476
• Main Author: 邓韧 李著信 樊友洪
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer Nature B.V 01.04.2007; Logistic Engineering University, Chongqing 400016, P. R. China
• Edition: English ed.
• Subjects: Asymptotic properties; Computer simulation; Dynamical systems; Lyapunov函数模型; Mathematical models; Networks; Neural networks; Nonlinear dynamics; Recurrent neural networks; Stability; Theorems; Wavelet; 稳定性; 递归小波神经网络; 非线性动态系统; recurrent wavelet neural networks; asymptotic stability; nonlinear dynamic system; Lyapunov function
• ISSN: 0253-4827; 1573-2754
• DOI: 10.1007/s10483-007-0407-z

Based on wavelet neural networks （WNNs） and recurrent neural networks （RNNs）, a class of models on recurrent wavelet neural networks （RWNNs） is proposed. The new networks possess the advantages of WNNs and RNNs. In this paper, asymptotic stability of RWNNs is researched.according to the Lyapunov theorem, and some theorems and formulae are given. The simulation results show the excellent performance of the networks in nonlinear dynamic system recognition.