本文已被:浏览 1529次 下载 2411次
Received:March 24, 2014 Revised:July 11, 2014
Received:March 24, 2014 Revised:July 11, 2014
中文摘要: 通过标准自适应共振理论神经网络(Adaptive Resonance Theory, ART), 设计和实现了一个字符识别器, 针对标准的ART1网络存在的不足, 即网络的学习不稳定, 对样本输入顺序比较敏感等问题, 给出了改进方法, 用C语言实现了这2种字符识别器, 实验结果表明这2种字符识别器能够对不同的字符进行识别, 改进方法比基于标准ART1网络具有更好的稳定性.
Abstract:Adaptive Resonance Theory (ART) neural network is analyzed in this paper. A character recognizer is designed and implemented based on the standard ART1 network, aiming at the shortcomings of the standard ART1 network, which concludes the unstablity of network learning and the over sensitiveness to the input sample sequence. This paper gives a method to improve the implementation in C 2 kind of identifier. Experimental validation of these two character recognizer can identify the different character. The improvement method based on standard ART1 network has better stability.
文章编号: 中图分类号: 文献标志码:
基金项目:国家自然科学基金(61272364);广东省学科建设专项资金(2013WYXM0122);深圳市科技计划项目及基础研究计划(JC201005270275A);深圳市战略性新兴产业发展专项资金 (JCYJ20120614144655154);北京师范大学珠海分校科研创新团队(201251006);北京师范大学珠海分校教改项目(201329)
引用文本:
杨戈,莫青青,黄静.基于ART1网络的字符识别器.计算机系统应用,2014,23(12):136-141
YANG Ge,MO Qing-Qing,HUANG Jing.Character Recognizer Based on ART1 Network.COMPUTER SYSTEMS APPLICATIONS,2014,23(12):136-141
杨戈,莫青青,黄静.基于ART1网络的字符识别器.计算机系统应用,2014,23(12):136-141
YANG Ge,MO Qing-Qing,HUANG Jing.Character Recognizer Based on ART1 Network.COMPUTER SYSTEMS APPLICATIONS,2014,23(12):136-141