首页> 外文会议>Machinee learning >Revision of Reduced Theories
【24h】

Revision of Reduced Theories

机译:简化理论的修订

获取原文
获取原文并翻译 | 示例

摘要

Revising a theory to cover a set of new data can be very difficult. When the theory is represented by propositional rules with uncertainty, many strength refinement problems are shown to be computationally intractable (NP-hard) to solve in a "deep" theory. In this paper, we show that when the same theory is represented in a reduced or flat structure some refinement problems are strictly easier to solve. We prove that some strength refinement problems that are NP-hard in the "deep" theory can be solved in polynomial time in the reduced theory, while some others still remain NP-hard.
机译:修改理论以涵盖一组新数据可能非常困难。当该理论由具有不确定性的命题规则表示时,许多强度细化问题显示为在“深度”理论中难以解决(NP难处理)。在本文中,我们表明,当相同的理论以简化或平坦的结构表示时,某些改进问题严格而言更容易解决。我们证明,在“深层”理论中一些难于解决NP问题的强度细化问题可以在归约理论中的多项式时间内解决,而另一些问题仍然对NP难解决。

著录项

  • 来源
    《Machinee learning》|1991年|519-523|共5页
  • 会议地点 Evanston IL(US);Evanston IL(US)
  • 作者单位

    Department of Computer Science University of Western Ontario London, Ontario, Canada N6A 5B7;

    Department of Computer Science University of South Carolina Columbia, SC 29208, U.S.A.;

  • 会议组织
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 计算机的应用;
  • 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