articlePLoS ONEJul 10, 2015GOLD OA

On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation

SBSebastian BachABAlexander BinderGMGrégoire MontavonFKFrederick KlauschenKMKlaus‐Robert Müller

Technische Universität Berlin · Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute · +3 more institutions

PubMed
Indexed incrossrefdoajpubmed

Abstract

Understanding and interpreting classification decisions of automated image classification systems is of high value in many applications, as it allows to verify the reasoning of the system and provides additional information to the human expert. Although machine learning methods are solving very successfully a plethora of tasks, they have in most cases the disadvantage of acting as a black box, not providing any information about what made them arrive at a particular decision. This work proposes a general solution to the problem of understanding classification decisions by pixel-wise decomposition of nonlinear classifiers. We introduce a methodology that allows to visualize the contributions of single pixels to…

Citation impact

4,555
total citations
FWCI
49.97
Percentile
100%
References
56
Citations per year

Authors

6

Topics & keywords

Topics
Keywords
  • MNIST database
  • Computer science
  • Artificial intelligence
  • Pixel
  • Pascal (unit)
  • Machine learning
  • Pattern recognition (psychology)
  • Classifier (UML)
UN Sustainable Development Goals
  • Peace, Justice and strong institutions
No related works found for this paper.

Funding