基于视中枢神经机制的层次网络计算模型

在视皮层区中，有许多非常规整的柱形功能结构，它们形成的局域网络具有抽取视图像中最基本的特征的计算能力，相邻视神细胞则抑制机制和神经细胞的感受野为实现这样的并行计算能力提供了保证，并且以层的这种等级组构为许多心理现像提供了生理解释，这不仅对模式识别、计算机视觉有重要的价值，而且对人工智能系统的知识获取和知识表示都具有非常重要的意义，文中通过构造一个金字塔状的神经网络层次模型，来对模拟视网膜的输入点阵

A Hierarchical Model Based on Visual Cortex

The visual cortex consists of layers of neural cells. The cells, specifically the simple and complex cells, are arranged in a very orderly way. They are organized in narrow columns that cut across the layers of the cortex, each column continuing responds best when a specific visual image projected on the retina. In the language of pattern recognition, they work as feature extraction units. The architecture and mechanism of natural biological system , which processing visual image, are taken as a model for the development of artificial electrical system. The ANN algorithms are used to train the network for the acquisition of sensitivity to special feature. All these research are of great significance for knowledge representation, pattern recognition and computer vision, which are based on cognitive neuropsychology.