论文标题
时间序列：时间序列随机进化的输入样本说明
TimeREISE: Time-series Randomized Evolving Input Sample Explanation
论文作者
论文摘要
深神经网络是不同领域中最成功的分类器之一。但是，由于它们关于可解释性的局限性，其使用在安全关键环境中受到限制。可解释的人工智能的研究领域解决了这个问题。但是，大多数可解释性方法通过设计对齐图像方式。本文介绍了一种模型不可知归因方法，该方法与时间序列分类的上下文中的成功特别一致。与现有的方法相比，该方法显示出卓越的性能。 timerise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有关输入形状，并且不依赖于先前的数据知识。
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.
