Research Area:  Machine Learning
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.
Keywords:  
Deep Neural Networks
Machine Learning
Deep Learning
Author(s) Name:  Grégoire Montavon,Wojciech Samek,Klaus-Robert Müller
Journal name:  Digital Signal Processing
Conferrence name:  
Publisher name:  ELSEVIER
DOI:  10.1016/j.dsp.2017.10.011
Volume Information:  Volume 73, February 2018, Pages 1-15
Paper Link:   https://www.sciencedirect.com/science/article/pii/S1051200417302385