W
Wojciech Samek
Researcher at Heinrich Hertz Institute
Publications - 90
Citations - 11059
Wojciech Samek is an academic researcher from Heinrich Hertz Institute. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 25, co-authored 59 publications receiving 7433 citations. Previous affiliations of Wojciech Samek include Fraunhofer Society & Technical University of Berlin.
Papers
More filters
Journal ArticleDOI
Transferring Subspaces Between Subjects in Brain--Computer Interfacing
TL;DR: This novel approach to learning from other subjects aims to reduce the adverse effects of common nonstationarities, but does not transfer discriminative information, and can not only achieve a significant increase in performance but also allow for a neurophysiologically meaningful interpretation.
Journal ArticleDOI
Divergence-Based Framework for Common Spatial Patterns Algorithms
TL;DR: It is shown that the popular common spatial patterns (CSP) algorithm can be formulated as a divergence maximization problem and computed within this framework and unifies many of the recently proposed CSP variants in a principled manner.
Book ChapterDOI
Layer-Wise Relevance Propagation for Deep Neural Network Architectures
TL;DR: This work presents 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.
Book ChapterDOI
Detection of Face Morphing Attacks by Deep Learning
TL;DR: An automatic morphing pipeline is presented to generate morphing attacks, train neural networks based on this data and analyze their accuracy, and the accuracy of different well-known network architectures are compared.
Posted Content
Analyzing Classifiers: Fisher Vectors and Deep Neural Networks
TL;DR: In this article, a principled technique, Layer-wise Relevance Propagation (LRP), has been developed in order to better comprehend the inherent structured reasoning of complex nonlinear classification models such as Bag of Feature models or DNNs.