arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.00899cs.LGcs.AIstat.ML
收藏

弱监督学习器用于纠正AI错误并提供可证明的性能保证

Weakly Supervised Learners for Correction of AI Errors with Provable Performance Guarantees

King’s College London(伦敦国王学院);University of Leicester(莱斯特大学)

Ivan Y. Tyukin, Tatiana Tyukina, Daniel van Helden, Zedong Zheng, Evgeny M. Mirkes, Oliver J. Sutton, Qinghua Zhou, Alexander N. Gorban, Penelope Allison

AI总结:

本文提出一种弱监督AI错误纠正器,通过批准或拒绝底层分类器决策来调节其并弃权,并提供分布无关的性能保证,并在训练数据稀缺的现实图像分类任务中验证了其有效性。

摘要:

我们提出了一种处理AI错误的新方法,通过引入具有先验性能保证的弱监督AI错误纠正器来实现。这些AI纠正器是是辅助映射,其作用是通过批准或拒绝先前构建的底层分类器的决策来调节其决策。拒绝决策可以用作建议弃权(不执行)决策的信号。这项工作的一个关键技术重点是通过限制错误决策概率来为这些新的AI纠正器提供性能保证。这些界限是分布不可知的,并且不依赖于数据维度的假设。我们的经验示例说明了如何在训练数据稀缺的具有挑战性的现实任务中应用该框架以改进图像分类器的性能。summary_cn

英文摘要:

We present a new methodology for handling AI errors by introducing weakly supervised AI error correctors with a priori performance guarantees. These AI correctors are auxiliary maps whose role is to moderate the decisions of some previously constructed underlying classifier by either approving or rejecting its decisions. The rejection of a decision can be used as a signal to suggest abstaining from making a decision. A key technical focus of the work is in providing performance guarantees for these new AI correctors through bounds on the probabilities of incorrect decisions. These bounds are distribution agnostic and do not rely on assumptions on the data dimension. Our empirical example illustrates how the framework can be applied to improve the performance of an image classifier in a challenging real-world task where training data are scarce.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑