no code implementations • 27 Apr 2016 • Irene Sturm, Sebastian Bach, Wojciech Samek, Klaus-Robert Müller
With LRP a new quality of high-resolution assessment of neural activity can be reached.
no code implementations • 4 Apr 2016 • Alexander Binder, Grégoire Montavon, Sebastian Bach, Klaus-Robert Müller, Wojciech Samek
Layer-wise relevance propagation is a framework which allows to decompose the prediction of a deep neural network computed over a sample, e. g. an image, down to relevance scores for the single input dimensions of the sample such as subpixels of an image.
no code implementations • 21 Mar 2016 • Sebastian Bach, Alexander Binder, Klaus-Robert Müller, Wojciech Samek
We present an application of the Layer-wise Relevance Propagation (LRP) algorithm to state of the art deep convolutional neural networks and Fisher Vector classifiers to compare the image perception and prediction strategies of both classifiers with the use of visualized heatmaps.
4 code implementations • 8 Dec 2015 • Grégoire Montavon, Sebastian Bach, Alexander Binder, Wojciech Samek, Klaus-Robert Müller
Although our focus is on image classification, the method is applicable to a broad set of input data, learning tasks and network architectures.
no code implementations • CVPR 2016 • Sebastian Bach, Alexander Binder, Grégoire Montavon, Klaus-Robert Müller, Wojciech Samek
Fisher Vector classifiers and Deep Neural Networks (DNNs) are popular and successful algorithms for solving image classification problems.
1 code implementation • 21 Sep 2015 • Wojciech Samek, Alexander Binder, Grégoire Montavon, Sebastian Bach, Klaus-Robert Müller
Our main result is that the recently proposed Layer-wise Relevance Propagation (LRP) algorithm qualitatively and quantitatively provides a better explanation of what made a DNN arrive at a particular classification decision than the sensitivity-based approach or the deconvolution method.