Methods for interpreting and understanding deep neural networks
Methods for interpreting and understanding deep neural networks
复制标题
DOI：
10.1016/j.dsp.2017.10.011
复制
发表时间：
2018-02-01
影响因子：
2.9
通讯作者：
Mueller, Klaus-Robert
中科院分区：
文献类型：
--
作者：
Montavon, Gregoire;Samek, Wojciech;Mueller, Klaus-Robert
本文为解释深度神经网络模型和解释其预测问题提供了一个切入点。它是基于ICASSP 2017给出的教程。作为一篇教程，本文所涵盖的方法集并不详尽，但足以代表讨论可解释性、技术挑战和可能的应用程序方面的许多问题。本教程的第二部分重点介绍最近提出的分层相关传播（LRP）技术，我们将为此提供理论、建议和技巧，以便在实际数据上最有效地使用它。(C) 2017年作者。Elsevier Inc.出版。
This paper provides an entry point to the problem of interpreting a deep neural network model and explaining its predictions. It is based on a tutorial given at ICASSP 2017. As a tutorial paper, the set of methods covered here is not exhaustive, but sufficiently representative to discuss a number of questions in interpretability, technical challenges, and possible applications. The second part of the tutorial focuses on the recently proposed layer-wise relevance propagation (LRP) technique, for which we provide theory, recommendations, and tricks, to make most efficient use of it on real data. (C) 2017 The Authors. Published by Elsevier Inc.