Methods for interpreting and understanding deep neural networks

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...

Full description

Saved in:
Bibliographic Details
Published in:Digital signal processing 2018-02, Vol.73, p.1-15
Main Authors: Montavon, Grégoire, Samek, Wojciech, Müller, Klaus-Robert
Format: Article
Language:English
Subjects:
Activation maximization
Deep neural networks
Layer-wise relevance propagation
Sensitivity analysis
Taylor decomposition
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1051-2004
1095-4333
DOI:10.1016/j.dsp.2017.10.011