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 2108.08712cs.LGstat.ML
收藏

通过用例教授机器学习中的不确定性量化

Teaching Uncertainty Quantification in Machine Learning through Use Cases

German Research Center for Artificial Intelligence(德国人工智能研究中心)

Matias Valdenegro-Toro

摘要:

机器学习中的不确定性通常不作为一般知识在机器学习课程中教授。在本文中,我们提出了一个关于机器学习中不确定性的短期课程,并通过选择用例来补充课程,旨在引发讨论,让学生在编程环境中使用不确定性的概念。我们的用例涵盖了输出不确定性的概念、贝叶斯神经网络和权重分布、不确定性的来源以及分布外检测。我们希望这套课程和用例能够激励社区将这些重要的概念纳入人工智能安全课程。

英文摘要:

Uncertainty in machine learning is not generally taught as general knowledge in Machine Learning course curricula. In this paper we propose a short curriculum for a course about uncertainty in machine learning, and complement the course with a selection of use cases, aimed to trigger discussion and let students play with the concepts of uncertainty in a programming setting. Our use cases cover the concept of output uncertainty, Bayesian neural networks and weight distributions, sources of uncertainty, and out of distribution detection. We expect that this curriculum and set of use cases motivates the community to adopt these important concepts into courses for safety in AI.

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。

↑