Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Layer-wise relevance propagation for deep neural network architectures

: Binder, A.; Bach, S.; Montavon, G.; Müller, K.-R.; Samek, W.


Kim, K. J.; Joukov, N.:
Information Science and Applications (ICISA) 2016
Singapore: Springer, 2016 (Lecture notes in electrical engineering 376)
ISBN: 978-981-10-0557-2
ISBN: 978-981-10-0556-5
International Conference on Information Science and Applications (ICISA) <7, 2016, Ho Chi Minh>
Fraunhofer HHI ()

We present the application of layer-wise relevance propagation to several deep neural networks such as the BVLC reference neural net and googlenet trained on ImageNet and MIT Places datasets. Layer-wise relevance propagation is a method to compute scores for image pixels and image regions denoting the impact of the particular image region on the prediction of the classifier for one particular test image. We demonstrate the impact of different parameter settings on the resulting explanation.