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 2108.02497cs.LG
收藏

如何避免机器学习陷阱:面向学术研究人员的指南

How to avoid machine learning pitfalls: a guide for academic researchers

School of Mathematical and Computer Sciences, Heriot-Watt University(赫瑞瓦特大学数学与计算机科学学院)

Michael A. Lones

AI总结:

本文为学术研究人员提供了一份指南,系统梳理了机器学习实践中的常见错误,并详细说明了在模型构建、评估、比较和报告等五个阶段如何避免这些陷阱以得出有效结论。

摘要:

机器学习实践中的错误很常见,可能导致对机器学习的研究发现和产品失去信心。本指南概述了使用机器学习时出现的常见错误,以及如何避免这些错误。虽然任何具备机器学习技术基本理解的人都应能理解本指南,但它重点关注学术研究中特别令人担忧的问题,例如需要进行严格的比较并得出有效的结论。它涵盖了机器学习过程的五个阶段:模型构建前要做什么、如何可靠地构建模型、如何稳健地评估模型、如何公平地比较模型,以及如何报告结果。

英文摘要:

Mistakes in machine learning practice are commonplace, and can result in a loss of confidence in the findings and products of machine learning. This guide outlines common mistakes that occur when using machine learning, and what can be done to avoid them. Whilst it should be accessible to anyone with a basic understanding of machine learning techniques, it focuses on issues that are of particular concern within academic research, such as the need to do rigorous comparisons and reach valid conclusions. It covers five stages of the machine learning process: what to do before model building, how to reliably build models, how to robustly evaluate models, how to compare models fairly, and how to report results.

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。

↑