Figure-Ground Separation Using a Diffusion-Concentration Neural Network  

作　　者：郭宝龙 郭雷 

机构地区：[1]Department of Detection anil Instrument, Xidian University, Xi'an 710071, PRC

出　　处：《Chinese Science Bulletin》1994年第24期2086-2090,共5页

基　　金：Project supported by the National Natural Science Foundation of China, NHFC (863) and MRFC.

摘　　要：The mechanism of diffusion and concentration of neural activity is one of the basic laws of neuronal interaction in the cerebral cortex.The evidence shows that the lateral connections between neurons in the cerebral neocortex take the following structure: the short-range lateral connections are excitatory while the long-range ones are inhibitory.This note shows that the structure of connections is able both to diffuse and to concentrate information; that is, the short-range excitatory connections

关 键 词：NEURAL networks DIFFUSION and CONCENTRATION FIGURE-GROUND separation. 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]