首页 | 本学科首页   官方微博 | 高级检索  
     

ART2神经网络调整子系统结构的改进
引用本文:吕秀江,赵研,姚光顺,邓艳明.ART2神经网络调整子系统结构的改进[J].机械与电子,2005(11):62-64.
作者姓名:吕秀江  赵研  姚光顺  邓艳明
作者单位:1. 长春工业大学,吉林,长春,130012
2. 常德卷烟厂四平分厂,吉林,四平,136001
摘    要:ART2神经网络是按照自适应谐振理论建立的一种自组织、无监督的人工神经网络,可应用于连续的动态数据分类。但在实际应用中发现其理论存在“同相位不可分”的缺点。针对此问题提出了一种改进的ART2神经网络模型结构及其算法,进行了仿真,给出了与常用ART2网络所做仿真的结果比较。

关 键 词:ART2  神经网络  调整子系统
文章编号:1001-2257(2005)11-0062-02
收稿时间:2005-08-23
修稿时间:2005年8月23日

Improvements of ART2 Neural Network Adaptation System Patterns
LV Xiu-jiang,ZHAO Yan,YAO Guang-shun,DENG Yan-ming.Improvements of ART2 Neural Network Adaptation System Patterns[J].Machinery & Electronics,2005(11):62-64.
Authors:LV Xiu-jiang  ZHAO Yan  YAO Guang-shun  DENG Yan-ming
Affiliation:1. Changchun University of Technology, Changchun 130012, China; 2. Siping Branch Factory of Changde Cigarettes Factory, Siping 136001, China
Abstract:ART2 is a self-organized and unsupervised artificial neural network constructed from adaptive resonance theory which can be used to classify continuous active data. We have found that the theory is limited of the same phase data with different amplitudes and insensitivity to gradual change data during the simulation of data classified with ART2 neural network. Therefore,we propose a new neural network model based on adaptive resonance theory. We provide the model construction and relevant algorithm as well as the comparison with ART2.
Keywords:ART2  neural network  adaptation system
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号