Convergence analysis of a class of simplified background neural networks with two subnetworks
Convergence analysis of a class of simplified background neural networks with two subnetworks
复制标题
DOI：
10.1016/j.neucom.2011.08.002
复制
发表时间：
2011-11
期刊：
影响因子：
6
通讯作者：
Fang Xu;Zhang Yi
中科院分区：
文献类型：
--
作者：
Fang Xu;Zhang Yi
受Salinas（2003）在[1]中的发现和Oja（1982）在[2]中的开创性工作的启发，本文提出了一类简化的具有两个子网络的背景神经网络模型。一些基本的动力学性质，包括有界性，全局吸引性，稳定性和完全收敛性进行了严格的分析。本文的主要工作如下：（1）证明了新模型的有界性，并给出了全局吸引的条件。(2)得到了平衡点渐近稳定的条件。(3)通过构造新的能量函数证明了新网络的完全收敛性。最后，数值例子验证了我们的理论结果。
Motivated by Salinas's (2003) original discovery in [1] and inspired by Oja's (1982) seminal work in [2], in this paper, we propose a class of simplified background neural networks model with two subnetworks. Some basic dynamic properties including boundedness, global attractivity, stability, and complete convergence are analyzed rigorously. The main contributions in this paper are as follows: (1) The boundedness of the new model is verified and conditions for global attractivity are derived. (2) Conditions on asymptotically stable of equilibrium points are obtained. (3) Complete convergence for the new network is proved by constructing a novel energy function. Finally, numerical examples demonstrate our theoretical results.