首页 | 官方网站   微博 | 高级检索  
     

多层BP网络的研究及应用
引用本文:李伟,金锦良.多层BP网络的研究及应用[J].计算机应用与软件,1997,14(3):9-17,34.
作者姓名:李伟  金锦良
作者单位:复旦大学计算机科学系,复旦大学计算机科学系,复旦大学计算机科学系 上海 200433,上海 200433,上海 200433
摘    要:在本文中,我们用统计模式识别的方法分析了目前在模式识别中得到广泛应用的多层BP神经网络,揭示了具有线性输出单元的多层BP神经网络用作特征提取器和分类器时具有良好性能的原因。同时,我们设计了一个使用BP网络作为特征提取器和分类器时,普适的工件识别系统,对不能识别的样本,采用模糊推理技术,把传统的直观特征识别结果和多层BP网络结果特征级上融合,提高系统的性能。

关 键 词:神经网络  模糊推理  模式识别  BP网络

THE ANALYSIS AND APPLICATION OF MULTI-LEVEL BP NEURAL NETWORK
LI WEI JIN JINLIANG HE YONGBAO.THE ANALYSIS AND APPLICATION OF MULTI-LEVEL BP NEURAL NETWORK[J].Computer Applications and Software,1997,14(3):9-17,34.
Authors:LI WEI JIN JINLIANG HE YONGBAO
Abstract:In this paper, we analyze the widely used Multi-level BP Neural Network (MBPNN) with traditional statistics pattern recognition method and reveal why MBPNN with linear out-units has very well performance when used as feature extraction and pattern recognition. On the same time, we design a generalized part recognition system with MBPNN. As to the samples that have not been able to be recognized we adopt fuzzy logic to fusion obvious feature and MBPNN's feature, and increase the performance of the system.
Keywords:Neural network  fuzzy logic  pattern recognition  membership func- tion  BP algorithm    
本文献已被 CNKI 维普 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-23

京公网安备 11010802026262号