On Interpretability of Artificial Neural Networks: A Survey.
On Interpretability of Artificial Neural Networks: A Survey.
复制标题
DOI：
10.1109/trpms.2021.3066428
复制
发表时间：
2021-11
影响因子：
4.4
通讯作者：
Wang, Ge
中科院分区：
文献类型：
--
作者：
Fan, Feng-Lei;Xiong, Jinjun;Li, Mengzhou;Wang, Ge
近年来，以人工深度神经网络（DNN）为代表的深度学习在处理文本、图像、视频、图形等重要领域取得了巨大成功，但DNN的黑盒性质已成为其广泛应用于医疗诊断和治疗等关键任务应用的主要障碍之一。由于深度学习的巨大潜力，增加深度神经网络的可解释性最近引起了许多研究关注。在本文中，我们提出了一个简单而全面的分类解释性，系统地回顾了最近的研究，提高神经网络的解释性，描述解释性在医学中的应用，并讨论了未来可能的研究方向，如在模糊逻辑和脑科学。
Deep learning as represented by the artificial deep neural networks (DNNs) has achieved great success recently in many important areas that deal with text, images, videos, graphs, and so on. However, the black-box nature of DNNs has become one of the primary obstacles for their wide adoption in mission-critical applications such as medical diagnosis and therapy. Because of the huge potentials of deep learning, increasing the interpretability of deep neural networks has recently attracted much research attention. In this paper, we propose a simple but comprehensive taxonomy for interpretability, systematically review recent studies in improving interpretability of neural networks, describe applications of interpretability in medicine, and discuss possible future research directions of interpretability, such as in relation to fuzzy logic and brain science.