Perfetti R
Istituto di Elettronica, Perugia Univ.
IEEE Trans Neural Netw. 1995;6(5):1071-80. doi: 10.1109/72.410352.
In this paper, some new qualitative properties of discrete-time neural networks based on the "brain-state-in-a-box" model are presented. These properties concern both the characterization of equilibrium points and the global dynamical behavior. Next, the analysis results are used as guidelines in developing an efficient synthesis procedure for networks that function as associative memories. A constrained design algorithm is presented that gives completely stable dynamical neural networks sharing some interesting features. It is guaranteed the absence of nonbinary stable equilibria, that is stable states with nonsaturated components. It is guaranteed that in close proximity (Hamming distance one) of the stored patterns there is no other binary equilibrium point. Moreover, the presented method allows one to optimize a design parameter that controls the size of the attraction basins of the stored vectors and the accuracy needed in a digital realization of the network.
本文给出了基于“盒中脑状态”模型的离散时间神经网络的一些新的定性性质。这些性质涉及平衡点的特征描述和全局动力学行为。接下来，分析结果被用作指导方针，以开发一种有效的综合程序，用于作为联想存储器的网络。提出了一种约束设计算法，该算法给出了具有一些有趣特征的完全稳定的动态神经网络。保证不存在非二进制稳定平衡点，即具有不饱和分量的稳定状态。保证在存储模式的紧邻区域（汉明距离为一）内不存在其他二进制平衡点。此外，所提出的方法允许优化一个设计参数，该参数控制存储向量吸引盆的大小以及网络数字实现所需的精度。
