...
首页> 外文期刊>IEEE Transactions on Information Theory >Structural risk minimization over data-dependent hierarchies
【24h】

Structural risk minimization over data-dependent hierarchies

机译:通过数据依赖的层次结构最大程度地降低结构风险

获取原文
获取原文并翻译 | 示例
           

摘要

The paper introduces some generalizations of Vapnik's (1982) method of structural risk minimization (SRM). As well as making explicit some of the details on SRM, it provides a result that allows one to trade off errors on the training sample against improved generalization performance. It then considers the more general case when the hierarchy of classes is chosen in response to the data. A result is presented on the generalization performance of classifiers with a "large margin". This theoretically explains the impressive generalization performance of the maximal margin hyperplane algorithm of Vapnik and co-workers (which is the basis for their support vector machines). The paper concludes with a more general result in terms of "luckiness" functions, which provides a quite general way for exploiting serendipitous simplicity in observed data to obtain better prediction accuracy from small training sets. Four examples are given of such functions, including the Vapnik-Chervonenkis (1971) dimension measured on the sample.
机译:本文介绍了Vapnik(1982)的结构风险最小化(SRM)方法的一些概括。除了明确说明SRM的某些细节外,它还提供了一个结果,可以使人们在训练样本上的错误与提高的泛化性能之间进行权衡。然后,它考虑了更一般的情况,即根据数据选择类的层次结构。给出了具有“大余量”的分类器的泛化性能的结果。从理论上讲,这解释了Vapnik及其同事的最大余量超平面算法的令人印象深刻的概括性能(这是他们的支持向量机的基础)。本文以“运气”功能得出了更一般的结论,它提供了一种非常普遍的方法来利用观测数据中的偶然性简单性,以从小型训练集中获得更好的预测精度。给出了此类功能的四个示例,包括在样品上测量的Vapnik-Chervonenkis(1971)尺寸。

著录项

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