conference paper
Layer-Wise Relevance Propagation: An Overview
Grégoire Montavona✉, Alexander Binderb, Sebastian Lapuschkinc, Wojciech Samekc, Klaus‐Robert Müllerd e f
- aTechnische Universität Berlin, 10587, Berlin, Germany
- bSingapore University of Technology and Design, Singapore, 487372, Singapore
- cFraunhofer Heinrich Hertz Institute, 10587, Berlin, Germany
- dKorea University, Anam-dong, Seongbuk-gu, Seoul, 02841, Korea
- eMax Planck Institute for Informatics, 66123, Saarbrücken, Germany
- fSekretariat MAR 4-1, Technical University of Berlin, Berlin, Berlin, Germany
- ✉Corresponding author
Lecture notes in computer scienceSpringer Science+Business Media2019-01-01 933 citations64 references
Looking for the full paper…
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
No abstract is available from our sources. Use “Read paper” to view it.
TL;DRThis chapter gives a concise introduction to LRP with a discussion of how to implement propagation rules easily and efficiently, how the propagation procedure can be theoretically justified as a ‘deep Taylor decomposition’, how to choose the propagation rules at each layer to deliver high explanation quality, and how LRP can be extended to handle a variety of machine learning scenarios beyond deep neural networks. (Semantic Scholar)