| 基于间隔损失和L1范数调节的特征选择方法研究 |
| |
| 引用本文： | 潘巍,马培军,李东. 基于间隔损失和L1范数调节的特征选择方法研究[J]. 智能计算机与应用, 2012, 0(1): 8-10,15 |
| |
| 作者姓名： | 潘巍 马培军 李东 |
| |
| 作者单位： | 哈尔滨工业大学软件学院 |
| |
| 摘 要： | 特征评价和选择是机器学习和模式识别的重要步骤。为了获得稀疏特征子集,结合间隔损失评估策略和L1范数调节技术来获得一种有效的特征选择方法(MLFWL-L1),并将其应用到RBFSVM分类器。实验中,在UCI数据集上将提出的算法与Simba和ReliefF对比表明,验证所提出的算法是一种有效的特征选择方法。
|
| 关 键 词： | 特征选择 间隔损失 L1范数调节 |
Feature Selection Method based on Margin Loss and L1-norm Regulation |
| |
| PAN Wei,MA Peijun,LI Dong. Feature Selection Method based on Margin Loss and L1-norm Regulation[J]. INTELLIGENT COMPUTER AND APPLICATIONS, 2012, 0(1): 8-10,15 |
| |
| Authors: | PAN Wei MA Peijun LI Dong |
| |
| Affiliation: | (School of Software,Harbin Institute of Technology,Harbin 150001,China) |
| |
| Abstract: | Feature selection is an important task in machine learning and pattern recognition.The paper designs an algorithm for sparse feature subset.Then it combines margin loss with L1-norm regulation technology to obtain an effective feature selection method(MLFWL-L1),and applies it to RBFSVM classifier.Finally,the proposed technique is tested through a series of experiments with UCI data sets.Compared with four methods,the conclusion is that the proposed technique is effective and efficient. |
| |
| Keywords: | Feature Selection Margin Loss L1-norm Regulation |
| 本文献已被 CNKI 等数据库收录！ |
|
