Methods for interpreting and understanding deep neural networks
Grégoire MontavonDepartment of Electrical Engineering & Computer Science, Technische Universität Berlin, Marchstr. 23, Berlin 10587, GermanyWojciech SamekDepartment of Video Coding & Analytics, Fraunhofer Heinrich Hertz Institute, Einsteinufer 37, Berlin 10587, GermanyKlaus‐Robert MüllerDepartment of Brain & Cognitive Engineering, Korea University, Anam-dong 5ga, Seongbuk-gu, Seoul 136-713, South Korea
2017en
ABI
Abstract
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.
Identifiers
Citations and references
Cited by 30 references