...
首页> 外文期刊>Discrete Applied Mathematics >The capacity of monotonic functions
【24h】

The capacity of monotonic functions

机译:单调函数的容量

获取原文
获取原文并翻译 | 示例
           

摘要

We consider the class M of monotonically increasing binary output functions. M has considerable practical significance in machine learning and pattern recognition because prior information often suggests a monotonic relationship between input and output variables. The decision boundaries of monotonic classifiers are compared and contrasted with those of linear classifiers. M is shown to have a VC dimension of infinity, meaning that the VC bounds cannot guarantee generalization independent of input distribution. We demonstrate that when the input distribution is taken into account, however, the VC bounds become useful because the annealed VC entropy of M is modest for many distributions. Techniques for estimating the capacity and bounding the annealed VC entropy of M given the input distribution are presented and implemented. (C) 1998 Elsevier Science B.V. All rights reserved. [References: 9]
机译:我们考虑单调递增二进制输出函数的M类。 M在机器学习和模式识别中具有相当大的实际意义,因为先验信息通常表明输入和输出变量之间存在单调关系。将单调分类器的决策边界与线性分类器的决策边界进行比较和对比。 M的VC维被表示为无穷大,这意味着VC边界不能保证独立于输入分布的泛化。我们证明,当考虑输入分布时,VC边界变得有用,因为M的退火VC熵对于许多分布而言都是适度的。给出并实现了用于估计容量并限制给定输入分布的M的退火VC熵的技术。 (C)1998 Elsevier Science B.V.保留所有权利。 [参考:9]

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