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 2004.12524cs.LGstat.ML
收藏

序贯可解释性:在序贯数据背景下理解深度学习模型的方法、应用和未来方向

Sequential Interpretability: Methods, Applications, and Future Direction for Understanding Deep Learning Models in the Context of Sequential Data

University of Florida(佛罗里达大学)

Benjamin Shickel, Parisa Rashidi

摘要:

深度学习继续革新越来越多的关键应用领域,包括医疗、交通、金融和基础科学。尽管它们的预测能力有所提高,但由于现代深度学习模型的“黑匣子”性质,模型的透明度和人类可解释性仍然是一个重大挑战。在许多情况下,可解释性和性能之间的理想平衡主要是特定于任务的。以人为本的领域,如医疗保健,需要重新关注这些框架如何以及为什么会达到关键和潜在的生死攸关的决定。鉴于计算机视觉的深度学习的研究和经验成功的数量,大多数现有的可解释性研究都集中在图像处理技术上。相比之下,较少关注使用序列数据解释深度学习框架。鉴于最近深度学习在高度序列化领域(如自然语言处理和生理信号处理)的进步,对深度序列化解释的需求达到了历史最高水平。在本文中,我们回顾了当前用于解释涉及序列数据的深度学习技术的技术,确定了与非序列方法的相似之处,并讨论了序列可解释性研究的当前限制和未来途径。

英文摘要:

Deep learning continues to revolutionize an ever-growing number of critical application areas including healthcare, transportation, finance, and basic sciences. Despite their increased predictive power, model transparency and human explainability remain a significant challenge due to the "black box" nature of modern deep learning models. In many cases the desired balance between interpretability and performance is predominately task specific. Human-centric domains such as healthcare necessitate a renewed focus on understanding how and why these frameworks are arriving at critical and potentially life-or-death decisions. Given the quantity of research and empirical successes of deep learning for computer vision, most of the existing interpretability research has focused on image processing techniques. Comparatively, less attention has been paid to interpreting deep learning frameworks using sequential data. Given recent deep learning advancements in highly sequential domains such as natural language processing and physiological signal processing, the need for deep sequential explanations is at an all-time high. In this paper, we review current techniques for interpreting deep learning techniques involving sequential data, identify similarities to non-sequential methods, and discuss current limitations and future avenues of sequential interpretability research.

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。

↑