PatternNet and PatternLRP - Improving the interpretability of neural networks
PatternNet and PatternLRP - Improving the interpretability of neural networks
Pieter-Jan Kindermans,Kristof T. Schütt,2 Authors,Sven Dähne
2017 · DBLP: journals/corr/KindermansSAMD17
arXiv.org · 65 Citations
TLDR
An improved method is proposed that may serve as an extension for existing back-projection and decomposition techniques and formulate a quality criterion for explanation methods.