期刊文献+

二种构造性神经网络算法的对比

Comparison of Two Construction Algorithms in Neural Network
下载PDF
导出
摘要 描述Cascade-correlation和RBF-DDA(dynamic decay adjustment for RBFs)神经网络算法,以Proben1中的3个数据库(癌症数据库、糖尿病数据库、心脏病数据库)为例,阐述两种算法在训练神经网络中的应用,并对比这两种算法的性能。 This article describes cascade-correlation algorithm and dynamic decay adjustment for RBFs algorithm, and uses three database of Probenl (cancer,diabetes and heart)to probe and compare the application of the two algorithms in neural network training.
作者 曹志峰
机构地区 福建医科大学
出处 《石河子大学学报(自然科学版)》 CAS 2005年第5期650-653,共4页 Journal of Shihezi University(Natural Science)
关键词 CORRELATION RBF-DDA Probenl JavaNNS Cascade-correlation RBF-DDA Probenl JavaNNS
  • 相关文献

参考文献4

  • 1Fahlman S E,Lebiere C.The cascade-correlation learning architecture.In:Touretzky D S ed.advances in neural informati-on processing systems[M].Los Altos C A:Morgan Kaufmann,1990,524-532. 被引量:1
  • 2Fahlman S E.The recurrent cascade-correlation architecture.Technical report CMU-CS-91-100,school of computer science[R].Pittsburgh:Carnegie Mellon University,1991. 被引量:1
  • 3Michael R,Berthold.Boosting the performance of RBFnetworks with dynamic decay adjustment in Germany Tesauro D S Touretzky_and T K Leen-editors-Advances in neural information processing systems[M].Cambridge MA:MIT Press,1995,521-528. 被引量:1
  • 4Lutz Prechelt.Proben1-a set of neural network benchmark problems and benchmarking rules,technical report[R].Germany:The University of Karlsruhe,1994. 被引量:1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部