首页> 外文OA文献 >Selectively inhibiting learning bias for active sampling
【2h】

Selectively inhibiting learning bias for active sampling

机译:有选择地抑制主动采样的学习偏差

摘要

Efficient training of machine learning algorithms requires a reliable labeled set from the application domain. Usually, data labeling is a costly process. Therefore, a selective approach is desirable. Active learning has been successfully used to reduce the labeling effort, due to its parsimonious process of querying the labeler. Nevertheless, many active learning strategies are dependent on early predictions made by learning algorithms. This might be a major problem when the learner is still unable to provide reliable information. In this context, agnostic strategies can be convenient, since they spare internal learners - usually favoring exploratory queries. On the other hand, prospective queries could benefit from a learning bias. In this article, we highlight the advantages of the agnostic approach and propose how to explore some of them without foregoing prospection. A simple hybrid strategy and a visualization tool called ranking curves, are proposed as a proof of concept. The tool allowed to see clearly when the presence of a learner was possibly detrimental. Finally, the hybrid strategy was successfully compared to its counterpart in the literature, to pure agnostic strategies and to the usual baseline of the field.
机译:机器学习算法的有效培训需要来自应用程序域的可靠标记集。通常,数据标记是一个昂贵的过程。因此,期望有选择的方法。由于主动学习减少了查询标注的过程,因此主动学习已成功用于减少标注工作。但是,许多主动学习策略都依赖于学习算法做出的早期预测。当学习者仍然无法提供可靠的信息时,这可能是一个主要问题。在这种情况下,不可知论策略可能会很方便,因为它们可以省却内部学习者-通常偏向于探索性查询。另一方面,预期查询可以受益于学习偏见。在本文中,我们重点介绍了不可知论方法的优点,并提出了如何在不做任何预见的情况下探索其中的一些方法。作为概念证明,提出了一种简单的混合策略和一种称为等级曲线的可视化工具。该工具可以清楚地看到何时出现学习者有害的情况。最后,混合策略已成功地与文献中的同类策略,纯不可知论策略以及该领域的通常基准进行了比较。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利

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