arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.05084cs.LG
收藏

解释来自机器学习模型的预测:算法、用户和教学法

Explaining Predictions from Machine Learning Models: Algorithms, Users, and Pedagogy

Ana Lucic

摘要:

由于算法预测对人类的影响越来越大,模型的可解释性已经成为机器学习(ML)中的一个重要问题。解释不仅可以帮助用户理解为什么ML模型会做出某些预测,还可以帮助用户理解如何改变这些预测。在这篇论文中,我们从三个有利的角度来研究ML模型的可解释性:算法,用户和教学,并为可解释性问题提供了一些新的解决方案。

英文摘要:

Model explainability has become an important problem in machine learning (ML) due to the increased effect that algorithmic predictions have on humans. Explanations can help users understand not only why ML models make certain predictions, but also how these predictions can be changed. In this thesis, we examine the explainability of ML models from three vantage points: algorithms, users, and pedagogy, and contribute several novel solutions to the explainability problem.

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。

↑