PDF(189 KB)
二种构造性神经网络算法的对比
曹志峰,
PDF(189 KB)
PDF(189 KB)
二种构造性神经网络算法的对比
Comparison of Two Construction Algorithms in Neural Network
CAO Zh-ifeng
This article describes cascade-correlation algorithm and dynamic decay adjustment for RBFs algorithm, and uses three database of Proben1(cancer, diabetes and heart)to probe and compare the application of the two algorithms in neural network training.
/ "> Cascade-correlation / RBF-DDA / Proben1 / JavaNNS {{custom_keyword}} /
[1] Fahlman S E, Lebiere C.The cascade-correlation learning architecture.In:Touretzky D S ed.advances in neural informat-ion processing systems[M].Los Altos C A:Morgan Kaufmann, 1990, 524-532. [2] Fahlman S E.The recurrent cascade-correlation architecture.
Technical report CMU-CS-91-100, school of computer science [R].Pittsburgh:Carnegie Mellon University, 1991.
[3] Michael 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, 521528.
[4] Lutz Prechelt.Proben1-a set of neural network benchmark problems and benchmarking rules, technical report [R ].Germany:The University of Karlsruhe, 1994
总访问:90471,今日访问:304, 当前在线:10
/
| 〈 |
|
〉 |
