arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.07952cs.LGcs.AI
收藏

TimeREISE:时间序列随机演化输入样本解释

TimeREISE: Time-series Randomized Evolving Input Sample Explanation

DFKI GmbH(德国人工智能研究中心)

Dominique Mercier, Andreas Dengel, Sheraz Ahmed

摘要:

深度神经网络是跨不同领域最成功的分类器之一。然而,由于它们在可解释性方面的局限性,它们的使用仅限于安全关键环境。可解释的人工智能的研究领域解决了这个问题。然而,大多数可解释性方法通过设计与图像模态一致。本文介绍了TimeREISE模型不可知的归因方法,特别是对准成功的时间序列分类的上下文中。该方法表现出优越的性能相比,现有的方法,关于不同的完善的测量。TimeREISE适用于任何时间序列分类网络,其运行时不会以线性方式扩展输入形状,并且不依赖于先验数据知识。

英文摘要:

Deep neural networks are one of the most successful classifiers across different domains. However, due to their limitations concerning interpretability their use is limited in safety critical context. The research field of explainable artificial intelligence addresses this problem. However, most of the interpretability methods are aligned to the image modality by design. The paper introduces TimeREISE a model agnostic attribution method specifically aligned to success in the context of time series classification. The method shows superior performance compared to existing approaches concerning different well-established measurements. TimeREISE is applicable to any time series classification network, its runtime does not scale in a linear manner concerning the input shape and it does not rely on prior data knowledge.

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。

↑