一类递归小波神经网络的稳定性研究

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名

邮箱

手机号码

标题

留言内容

验证码

Discussion of Stability in a Class of Models on Recurrent Wavelet Neural Networks

摘要: 在小波神经网络（WNNs）和递归神经网络（RNNs）的基础上，提出了一类递归小波神经网络（RWNNs）模型，它具有两种网络模型的优点A·D2根据Liapunov渐近稳定理论，对该模型的渐近稳定性进行了研究，并给出了相关的定理和公式．仿真结果表明该模型对非线性动态系统有良好的辨识效果．
- 递归小波神经网络 /
- 渐近稳定性 /
- 非线性系统 /
- Liapunov函数
Abstract: Based on wavelet neural networks (WNNs) and recurrent neural networks (RNNs), a class of models on recurrent wavelet neural networks (RWNNs) was proposed. The new networks possess the advantages of WNNs and RNNs. Asymptotic stability of RWNNs was researched according to the Liapunov theorem. Some theorems and formulae were given. The simulation results show the excellent performance of the networks in nonlinear dynamic system recognition.
- recurrent wavelet neural networks /
- asymptotic stability /
- nonlinear dynamic system /
- Liapunov function

[1]	李银国，张邦礼，曹长修.小波神经网络及其结构设计方法[J].模式识别与人工智能，1997,10(3):197-205.
[2]	谢庆国，沈轶，万淑芸.Elman人工神经网络的收敛性分析[J].计算机工程与应用，2002,38(6):65-81.
[3]	林毅.一类新的离散时间递归RBF神经网络[J].计算技术与自动化，1999,18(3):18-21.
[4]	Daubechies I. Orthonormal basis of compactly supported wavelets[J].Comm Pure Appl Math,1988,41(7):909-996. doi: 10.1002/cpa.3160410705
[5]	LIU Mei-qin,CHEN Ji-da,LIAO Xiao-xin.Discussion of stability in a class of models on recurrent radial basis function neural networks[J].Control Theory & Applications,2000,17(6):919—928.