...
首页> 外文期刊>Journal of machine learning research >Activized Learning: Transforming Passive to Active with Improved Label Complexity
【24h】

Activized Learning: Transforming Passive to Active with Improved Label Complexity

机译:主动学习:通过改进标签复杂性将被动转变为主动

获取原文
           

摘要

We study the theoretical advantages of active learning over passive learning. Specifically, we prove that, in noise-free classifier learning for VC classes, any passive learning algorithm can be transformed into an active learning algorithm with asymptotically strictly superior label complexity for all nontrivial target functions and distributions. We further provide a general characterization of the magnitudes of these improvements in terms of a novel generalization of the disagreement coefficient. We also extend these results to active learning in the presence of label noise, and find that even under broad classes of noise distributions, we can typically guarantee strict improvements over the known results for passive learning. color="gray">
机译:我们研究了主动学习相对于被动学习的理论优势。具体而言,我们证明,在针对VC类的无噪声分类器学习中,对于所有非平凡的目标函数和分布,任何被动学习算法都可以转化为具有渐近严格地优越的标签复杂度的主动学习算法。我们进一步以分歧系数的新颖概括性提供了这些改进幅度的一般特征。我们还将这些结果扩展到存在标签噪声的情况下的主动学习,并且发现,即使在广泛的噪声分布类别下,我们通常也可以保证对已知的被动学习结果进行严格的改进。 color =“ gray”>

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