Relaxation of the stability condition of the complex-valued neural networks
Relaxation of the stability condition of the complex-valued neural networks
复制标题
DOI：
10.1109/72.950156
复制
发表时间：
2001-09
影响因子：
--
通讯作者：
D. Lee
中科院分区：
文献类型：
--
作者：
D. Lee
Jankuwski等人（1996）提出了一种能够存储和调用灰度图像的复值神经网络（CVNN）。然而，为了保持网络的稳定性，CVNN的权矩阵必须是厄米矩阵，且具有非负对角项。厄米假设给网络的物理实现和实际应用带来了困难。本文导出了一个新的稳定性条件。所得结果不仅允许对连接矩阵的厄米假设有一点松弛，而且推广了已有的一些结果。
Jankuwski et al. (1996) have proposed a complex-valued neural network (CVNN) that is capable of storing and recalling gray-scale images. However, the weight matrix of the CVNN must be Hermitian with nonnegative diagonal entries in order to preserve the stability of the network. The Hermitian assumption poses difficulties in both physical realizations and practical applications of the networks. In this paper, a new stability condition is derived. The obtained result not only permits a little relaxation on the Hermitian assumption of the connection matrix, but also generalizes some existing results.