A NEURAL NETWORK MODEL FOR INVARIANT PATTERN-RECOGNITION

被引：11

作者：

SRINIVASA, N

JOUANEH, M

机构：

[1] department of Mechanical Engineering, University of Rhode Island, Kingston

来源：

IEEE TRANSACTIONS ON SIGNAL PROCESSING | 1992年 / 40卷 / 06期

关键词：

D O I：

10.1109/78.139270

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

A neural network model is proposed to achieve invariant pattern recognition to binary inputs based on a combination of the invariance net and the ART1 neural network. Computer simulations show that the new network is plastic to unfamiliar inputs and requires no explicit training of the inputs.

引用

页码：1595 / 1598

页数：4