USING MULTI-KOHONEN SELF-ORGANIZING MAPS FOR MODELING VISUAL PERCEPTION

被引：0

作者：

Collobert, Michel ^{[1
]}

机构：

[1] France Telecom R&D IRIS VIA, F-22307 Lannion, France

来源：

COMPUTER VISION AND GRAPHICS (ICCVG 2004) | 2006年 / 32卷

关键词：

Distributed perception; configuration of activity; Kohonen maps; somatosensory areas; neuron; chaos; multisensoriality; grandmother neuron;

D O I：

10.1007/1-4020-4179-9_150

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents a new organizing principle for perceptual systems based on multiple Kohonen self organizing maps. These maps arc arranged in order to model the global brain activity as seen on tomography pictures. In contrast to most of neural network models, a perceived object or knowledge is not represented by the final activity of a single neuron but by a configuration of activity of the whole neurons' set.

引用

页码：1031 / 1036

页数：6