Methods for interpreting and understanding deep neural networks

Citation data:

Digital Signal Processing, ISSN: 1051-2004, Vol: 73, Page: 1-15

Publication Year:
Usage 4
Abstract Views 2
Link-outs 2
Captures 589
Readers 589
Social Media 121
Tweets 113
Shares, Likes & Comments 8
Citations 26
Citation Indexes 26
Repository URL:
Montavon, Grégoire; Samek, Wojciech; Müller, Klaus-Robert
Elsevier BV
Computer Science; Engineering; Computer Science - Machine Learning; Statistics - Machine Learning
Most Recent Tweet View All Tweets
review description
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.