首页 | 本学科首页   官方微博 | 高级检索  
     

ART-2神经网络的改进及建模实现
引用本文:丛爽,郑毅松,王怡雯.ART-2神经网络的改进及建模实现[J].计算机工程与应用,2002,38(14):25-27,42.
作者姓名:丛爽  郑毅松  王怡雯
作者单位:中国科学技术大学自动化系,合肥,230027
基金项目:中国科学院优秀青年学者奖基金资助
摘    要:指出了传统的ART-2神经网络对渐变过程不敏感的局限性,提出了一种新的改进算法。并对ART-2网络进行建模,通过与其它建模方法的对比,详尽讨论了ART-2的建模方法及特点。最后通过应用改进算法解决了原先模型中的“模式漂移”现象,使模型性能得到了明显的改善。

关 键 词:模式识别  神经网络  系统建模  ART-2  模式漂移  串并联模型
文章编号:1002-8331-(2002)14-0025-03

The Improvement and Modeling Implementation of ART-2 Neural Network
Cong Shuang Zheng Yisong Wang Yiwen.The Improvement and Modeling Implementation of ART-2 Neural Network[J].Computer Engineering and Applications,2002,38(14):25-27,42.
Authors:Cong Shuang Zheng Yisong Wang Yiwen
Abstract:The paper indicates the limitation of the insensitivity for gradual change process of ART-2Neural Network,and brings forward a new refinement algorithm.The ART-2Network is rebuilt to model actual systems.The paper dis-cusses the modeling method and characteristic of the ART-2network by comparing with other modeling methods.Final-ly,the problem of"pattern drifting"is successfully resolved by applying the refinement algorithm to the ART-2.The per-formance of the new model is obviously improved.
Keywords:pattern recognition  neural network  system modeling  ART-2  pattern drifting  series and parallel model
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