应用信噪比理论分析复相角神经网络的存储容量

The Analysis of the Storage Capacity of the Complex Phasor Neural Network Using Signal-to-Noise Theory

本文应用信噪比理论分析了复相角神经网络模型的存储容量。分析和研究结果表明，当神经元转动态的数目很小时，模型的存储容量与Ｈｏｐｆｉｅｌｄ神经网络模型的存储容量相同；当神经元转动态的数目很大时，存储容量与神经元转动态数目的平方成反比。

In this paper, using the signal-to-noise theory the storage capacity of the complex phasor neural network was analysed, The analysis indicates that the storage capacity of the network is equal to that of the Hopfield model if the number of the states of neurons is small; and the storage capacity of the network is inversely proportional to the square of the number of the states of neurons if the number of the states of neurons is large.