| 极限学习机的快速留一交叉验证算法 |
| |
| 引用本文： | 刘学艺,李平,郜传厚.极限学习机的快速留一交叉验证算法[J].上海交通大学学报,2011,45(8):1140-1145. |
| |
| 作者姓名： | 刘学艺 李平 郜传厚 |
| |
| 作者单位： | （浙江大学 a.航空航天学院； b.工业控制研究所； c.数学系，杭州 310027） |
| |
| 基金项目： | 国家高技术研究发展计划(863)项目(2006AA04Z184); 国家自然科学基金资助项目(10901139,60911130510,60874029) |
| |
| 摘 要： | 针对回归和分类问题，提出一种极限学习机(Extreme Learning Machine, ELM)的快速留一交叉验证算法，并从理论和数值仿真两方面说明其有效性.结果表明，该算法避免了以训练样本数量N次的ELM模型的显式训练，其计算复杂度与N仅呈线性趋势增长，即O(N).即使在处理大型数据集建模问题时，该算法仍然可以快速地进行ELM模型的选择和评价.通过人工和实际数据集上的仿真实验，验证了该快速留一交叉验证算法的有效性.
|
| 关 键 词： | 极限学习机 留一法 交叉验证 计算复杂性 |
| 收稿时间： | 2011-03-15 |
Fast Leave-One-Out Cross-Validation Algorithm for Extreme Learning Machine |
| |
| LIU Xue-yia,LI Pinga,b,GAO Chuan-houc.Fast Leave-One-Out Cross-Validation Algorithm for Extreme Learning Machine[J].Journal of Shanghai Jiaotong University,2011,45(8):1140-1145. |
| |
| Authors: | LIU Xue-yia LI Pinga b GAO Chuan-houc |
| |
| Institution: | (a. School of Aeronautics and Astronautics; b. Institute of Industrial Process Control;c. Department of Mathematics, Zhejiang University, Hangzhou 310027, China) |
| |
| Abstract: | Leave-one-out cross-validation has proved to be near capable of giving the unbiased estimation of the generalization performance of statistical models,and thus can provide a reliable criterion for model selection and comparison.For this reason,the current paper presented a fast leave-one-out cross-validation algorithm in the framework of extreme learning machines(ELMs) with respect to both regression and classification problems,which can avoid training explicitly and just has the complexity of O(N) for a da... |
| |
| Keywords: | extreme learning machine(ELM) leave-one-out cross-validation computational complexity |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《上海交通大学学报》浏览原始摘要信息 |
| 点击此处可从《上海交通大学学报》下载免费的PDF全文 |
