Analysis of Neural Networks with Redundancy

被引：27

作者：

Izui, Yoshio ^{[1
]}

Pentland, Alex ^{[1
]}

机构：

[1] MIT, Vis Sci Grp, Media Lab, Cambridge, MA 02139 USA

来源：

NEURAL COMPUTATION | 1990年 / 2卷 / 02期

关键词：

D O I：

10.1162/neco.1990.2.2.226

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Biological systems have a large degree of redundancy, a fact that is usually thought to have little effect beyond providing reliable function despite the death of individual neurons. We have discovered, however, that redundancy can qualitatively change the computations carried out by a network. We prove that for both feedforward and feedback networks the simple duplication of nodes and connections results in more accurate, faster, and more stable computation.

引用

页码：226 / 238

页数：13