arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.07780cs.CVcs.AIcs.LGq-bio.NC
收藏

深度神经网络中的捷径学习

Shortcut Learning in Deep Neural Networks

University of Tübingen(蒂宾根大学);International Max Planck Research School for Intelligent Systems(国际马克斯·普朗克智能系统研究院);University of Toronto(多伦多大学);Vector Institute(向量研究所)

Robert Geirhos, Jörn-Henrik Jacobsen, Claudio Michaelis, Richard Zemel, Wieland Brendel, Matthias Bethge, Felix A. Wichmann

AI总结:

本文指出深度学习的许多问题源于捷径学习现象,即模型在标准基准上表现良好但难以泛化到现实场景,并基于此为模型解释和基准测试提出建议以提升鲁棒性和可迁移性。

摘要:

深度学习引发了当前人工智能的崛起,是当今机器智能的主力。大量成功案例迅速遍布科学、工业和社会,但其局限性直到最近才引起关注。在本文中,我们试图提炼出深度学习的许多问题如何被视为同一潜在问题的不同症状:捷径学习。捷径是在标准基准上表现良好但无法转移到更具挑战性的测试条件(如现实世界场景)的决策规则。类似的问题在比较心理学、教育学和语言学中也有报道,这表明捷径学习可能是学习系统(无论是生物的还是人工的)的共同特征。基于这些观察,我们为模型解释和基准测试制定了一系列建议,突出了机器学习在提高从实验室到现实世界应用的鲁棒性和可迁移性方面的最新进展。

英文摘要:

Deep learning has triggered the current rise of artificial intelligence and is the workhorse of today's machine intelligence. Numerous success stories have rapidly spread all over science, industry and society, but its limitations have only recently come into focus. In this perspective we seek to distill how many of deep learning's problems can be seen as different symptoms of the same underlying problem: shortcut learning. Shortcuts are decision rules that perform well on standard benchmarks but fail to transfer to more challenging testing conditions, such as real-world scenarios. Related issues are known in Comparative Psychology, Education and Linguistics, suggesting that shortcut learning may be a common characteristic of learning systems, biological and artificial alike. Based on these observations, we develop a set of recommendations for model interpretation and benchmarking, highlighting recent advances in machine learning to improve robustness and transferability from the lab to real-world applications.

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。

↑