...
首页> 外文期刊>Discrete Applied Mathematics >Generalization error bounds for the logical analysis of data
【24h】

Generalization error bounds for the logical analysis of data

机译:数据逻辑分析的泛化误差范围

获取原文
获取原文并翻译 | 示例
           

摘要

This paper analyzes the predictive performance of standard techniques for the 'logical analysis of data' (LAD), within a probabilistic framework. It does so by bounding the generalization error of related polynomial threshold functions in terms of their complexity and how well they fit the training data. We also quantify the predictive accuracy in terms of the extent to which there is a large separation (a 'large margin') between (most of) the positive and negative observations.
机译:本文在概率框架内分析了“数据逻辑分析”(LAD)的标准技术的预测性能。通过限制相关多项式阈值函数的泛化误差以及复杂度和拟合数据的拟合程度,可以做到这一点。我们还根据(大多数)正面和负面观察之间的较大差异(“大余量”)来量化预测准确性。

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