GAM模型稳定性分析及其在图像识别中的应用

王传栋; 陈蕾; 杨庚; 孙知信

doi:10.11834/jig.20110618

图像分析和识别 | 浏览量 : 0 下载量: 188 CSCD: 0

PDF
导出
分享
收藏
专辑

GAM模型稳定性分析及其在图像识别中的应用
Stability analysis of Gauss Auto-associative Memory model and its application on image recognition
2011年16卷第6期页码：1022-1029
网络出版：2011-06-15，

纸质出版：2011
DOI： 10.11834/jig.20110618
稿件说明：

移动端阅览

王传栋, 陈蕾, 杨庚, 孙知信. GAM模型稳定性分析及其在图像识别中的应用[J]. 中国图象图形学报, 2011,16(6):1022-1029. DOI： 10.11834/jig.20110618.

Stability analysis of Gauss Auto-associative Memory model and its application on image recognition[J]. Journal of Image and Graphics, 2011, 16(6): 1022-1029. DOI： 10.11834/jig.20110618.

摘要

多值指数关联联想记忆模型（MMECAM）是一种高存储容量的自联想记忆神经网络。在详细分析其优缺点的基础上，通过改进MMECAM模型的更新规则，首先提出一个新的高斯自联想记忆模型（GAM），然后通过定义简单的能量函数从理论上证明其在同、异步方式下的稳定性，从而保证所存储的模式能最终成为GAM的稳定点；其次，通过引入一般相似性测度进一步提出广义GAM模型（G-GAMs）框架，使得GAM模型成为其特例;最后，将GAM模型应用于单样本图像识别，计算机模拟证实了该模型的鲁棒性能。

Abstract

Modified Multi-valued Exponential Correlation Associative Memory Model (MMECAM) is a neural network with higher storage capacity. In this paper

based on the analyses of the strengths and weaknesses of MMECAM

a new Gauss Auto-associative Memory Model (GAM) is proposed by modifying its update rule. Then the stability of the proposed GAM is tested in synchronous and asynchronous update modes with a defined energy function

which ensures that the learnt patterns become stable points of the GAM. Further

a framework of Generalized GAM models (G-GAMs) is presented by introducing general similarity measures which makes GAM become its special cases. Finally

the GAM is applied to image recognition from a single sample per image successfully

and the computer simulation results verify GAM’s robust performance.