论文部分内容阅读
证明了具有零对角的厄米联结矩阵的异步离散复相角神经网络模型在其动力学演化过程中，网络的能量函数单调递减，网络最终将稳定在一个不动点吸引子上；当网络的神经元个数远大于存贮图象数时，随机存贮图象在能量函数空间中对应一能量极小点，因此存贮图象为网络的不动点吸引子．
It is proved that the energy function of the network decreases monotonically during the evolution of the dynamical evolution of an asynchronous discrete complex phasic neural network model with zero diagonal Hermite matrices. The network eventually stabilizes on a fixed point attractor. When the network The number of neurons is much larger than the number of stored images, the stored image corresponds to an energy minimum in the energy function space, so the stored image is the fixed point attractor of the network.