首页> 外文会议>Discovery science >Unsupervised Classifier Selection Based on Two-Sample Test
【24h】

Unsupervised Classifier Selection Based on Two-Sample Test

机译:基于两样本检验的无监督分类器选择

获取原文
获取原文并翻译 | 示例

摘要

We propose a well-founded method of ranking a pool of m trained classifiers by their suitability for the current input of n instances. It can be used when dynamically selecting a single classifier as well as in weighting the base classifiers in an ensemble. No classifiers are executed during the process. Thus, the n instances, based on which we select the classifier, can as well be unlabeled. This is rare in previous work. The method works by comparing the training distributions of classifiers with the input distribution. Hence, the feasibility for unsupervised classification comes with a price of maintaining a small sample of the training data for each classifier in the pool.rnIn the general case our method takes time O(m(t + n)~2) and space O(mt + n), where t is the size of the stored sample from the training distribution for each classifier. However, for commonly used Gaussian and polynomial kernel functions we can execute the method more efficiently. In our experiments the proposed method was found to be accurate.
机译:我们提出了一种很好的方法,可以根据m个训练好的分类器对n个实例的当前输入的适合性来对它们分类。在动态选择单个分类器以及对集合中的基本分类器加权时,可以使用它。在此过程中不会执行任何分类器。因此,我们根据其选择分类器的n个实例也可以不加标签。这在以前的工作中很少见。该方法通过将分类器的训练分布与输入分布进行比较来工作。因此,无监督分类的可行性是以为池中每个分类器维护少量训练数据样本为代价的.rn在一般情况下,我们的方法需要时间O(m(t + n)〜2)和空间O( mt + n),其中t是每个分类器从训练分布中存储的样本的大小。但是,对于常用的高斯和多项式内核函数,我们可以更有效地执行该方法。在我们的实验中,发现所提出的方法是准确的。

著录项

  • 来源
    《Discovery science》|2008年|28-39|共12页
  • 会议地点 Budapest(HU);Budapest(HU)
  • 作者单位

    Department of Software Systems, Tampere University of Technology P.O. Box 553 (Korkeakoulunkatu 1), FI-33101 Tampere, Finland;

    Department of Software Systems, Tampere University of Technology P.O. Box 553 (Korkeakoulunkatu 1), FI-33101 Tampere, Finland;

    Department of Software Systems, Tampere University of Technology P.O. Box 553 (Korkeakoulunkatu 1), FI-33101 Tampere, Finland;

  • 会议组织
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 人工智能理论;
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号