期刊文献+

组合式前馈神经网络研究

Combinations of Neural Networks and its Application
在线阅读 下载PDF
导出
摘要 本文首先讨论了组合式前馈神经网络原理和一般设计方法, 然后用两个仿真实验展示了组合式前馈神经网络在处理函数逼近和模式分类问题上的有效性。 In this paper, we discuss the idea of linear combinations of neural networks. Experimental results based on simulated data are included. For our examples, the approxinmation accuracy and recognition effect resulting from using combining neural networks is better then single neural network.
作者 杨华民
出处 《长春光学精密机械学院学报》 1998年第3期39-43,共5页 Journal of Changchun Institute of Optics and Fine Mechanics
基金 国家兵器 "九五" 预研基金
关键词 前馈 神经网络 函数逼近 模式分类 组合式 Feedforward neural networks Function approximation, Pattern classification
  • 相关文献

参考文献6

  • 1杨华民,龚跃.多元非参数回归建模的神经网络方法[J].长春光学精密机械学院学报,1997,20(2):51-55. 被引量:2
  • 2杨华民,姜会林,龚跃,刘炯,李平.基于神经网络的多种文字识别系统的集成方法[J].兵工学报,1998,19(4):339-343. 被引量:1
  • 3Hashem S and Schmeiser B. Improving model accuracy using optimal linear combinations of trained newral networks. IEEE Transactions on neural networks, 1995, 6(3): 792-794.
  • 4Clemen R T. Combining forecasts: A review and annotated bibliography. International Journal of Forecasting, 1989, 5:559-583.
  • 5Hashem S and Schmeiser B. Approximating a function and its derivatives using MSE-optimal linear combinations of trained feedforward neural networks, in Proceedings of the 1993 World congress on Neural Networks, NEW Jersey, Lawrence Erlbaum Associates, 1993,1 : 17-620.
  • 6Alpaydin E. Multiple networks for function learning, in proceedings of the 1993 IEEE Intermational Conference on Neural Networks, IEEE, Apr. 1993,1:9-14.

二级参考文献3

共引文献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