Nozawa Hiroshi
Development Division, Nikon Systems Inc., 26-2, Futaba 2-chrome, Shinagawa-ku, Tokyo 140, Japan.
Chaos. 1992 Jul;2(3):377-386. doi: 10.1063/1.165880.
First, a neural network model as the globally coupled map (GCM) is proposed. The model is obtained by modification of a Hopfield network model that has a negative self-feedback connection. Second, information processed by this model is interpreted in terms of the variety of the maps acting on the network elements, and a new, dynamic information processing model is described. The search for information using vague keywords, and solution of the traveling salesman problem (TSP) are introduced as applications.
首先，提出了一种作为全局耦合映射（GCM）的神经网络模型。该模型是通过对具有负自反馈连接的霍普菲尔德网络模型进行修改而获得的。其次，根据作用于网络元件的映射的多样性来解释该模型处理的信息，并描述了一种新的动态信息处理模型。作为应用，介绍了使用模糊关键词搜索信息以及旅行商问题（TSP）的解决方案。
