| 基于m-相依序列的学习机器相对一致收敛的界 |
| |
| 引用本文： | 王华丽.基于m-相依序列的学习机器相对一致收敛的界[J].襄樊学院学报,2011,32(11):5-8. |
| |
| 作者姓名： | 王华丽 |
| |
| 作者单位： | 襄樊学院数学与计算机科学学院,湖北襄阳,441053 |
| |
| 摘 要： | 为了研究m-相依序列下学习机器的推广性能,把基于独立同分布的结果推广到m-相依序列,建立采用ERM算法的学习机器的经验风险到它的期望风险相对一致收敛速率的界.并对m-相依序列现有的结论进行改进,得到了m-相依序列下,采用经验风险最小化算法学习机器的推广性能的界.
|
| 关 键 词： | 学习机器 ERM算法 相对一致收敛 m-相依序列 |
Bounds on the Rate of Relative Uniform Convergence for Learning Machine with m-dependent Processes |
| |
| WANG Hua-li.Bounds on the Rate of Relative Uniform Convergence for Learning Machine with m-dependent Processes[J].Journal of Xiangfan University,2011,32(11):5-8. |
| |
| Authors: | WANG Hua-li |
| |
| Institution: | WANG Hua-li(School of Mathematical and Computer Sciences,Xiangfan University,Xiangyang 441053,China) |
| |
| Abstract: | The generalization performance is the main purpose of machine learning theoretical research.To study the generalization ability with the dependent observations in this paper,we extend the results to the case where the i.i.d.sequence replaced by m-dependent processes.We derive the bounds on the rate of relative uniform convergence of the empirical risks to their expected risks,and improve current results with m-dependent processes.We also establish the bound that describes the generalization ability of ERM(E... |
| |
| Keywords: | Learning machine ERM algorithm Relative uniform convergence m-dependent processes |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
