| 具线性可分训练样本时在线BP神经网络的有限收敛性 |
| |
| 引用本文： | 邵郅邛,吴微,杨洁.具线性可分训练样本时在线BP神经网络的有限收敛性[J].数学研究及应用,2006,26(3):451-456. |
| |
| 作者姓名： | 邵郅邛 吴微 杨洁 |
| |
| 作者单位： | 大连理工大学应用数学系,辽宁,大连,116023 |
| |
| 基金项目： | the National Natural science Foundation of China (10471017)，the Basic Research Program of the National Defence Committee of Science,Technology and Industry of China (K1400060406) |
| |
| 摘 要： | 当训练样本线性可分时,本文证明前馈神经网络的在线BP算法是有限次收敛的．
|
| 关 键 词： | 非线性前馈神经网络 在线BP算法 有限收敛性 线性可分训练样本 |
| 文章编号： | 1000-341X(2006)03-0451-06 |
| 收稿时间： | 10 10 2004 12:00AM |
| 修稿时间： | 2004年10月10 |
Finite Convergence of On-line BP Neural Networks with Linearly Separable Training Patterns |
| |
| SHAO Zhi-qiong,WU Wei and YANG Jie.Finite Convergence of On-line BP Neural Networks with Linearly Separable Training Patterns[J].Journal of Mathematical Research with Applications,2006,26(3):451-456. |
| |
| Authors: | SHAO Zhi-qiong WU Wei and YANG Jie |
| |
| Institution: | Dept. of Appl. Math., Dalian University of Technology, Liaoning 116023, China;Dept. of Appl. Math., Dalian University of Technology, Liaoning 116023, China;Dept. of Appl. Math., Dalian University of Technology, Liaoning 116023, China |
| |
| Abstract: | In this paper we prove a finite convergence of online BP algorithms for nonlinear feedforward neural networks when the training patterns are linearly separable. |
| |
| Keywords: | nonlinear feedforward neural networks online BP algorithms finite convergence linearly separable training patterns |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《数学研究及应用》浏览原始摘要信息 |
| 点击此处可从《数学研究及应用》下载免费的PDF全文 |
