K
Klaus-Robert Müller
Researcher at Technical University of Berlin
Publications - 799
Citations - 98394
Klaus-Robert Müller is an academic researcher from Technical University of Berlin. The author has contributed to research in topics: Artificial neural network & Computer science. The author has an hindex of 129, co-authored 764 publications receiving 79391 citations. Previous affiliations of Klaus-Robert Müller include Korea University & University of Tokyo.
Papers
More filters
Journal ArticleDOI
Towards explaining anomalies: A deep Taylor decomposition of one-class models
Jacob R. Kauffmann,Klaus-Robert Müller,Klaus-Robert Müller,Klaus-Robert Müller,Grégoire Montavon +4 more
TL;DR: In this paper, the authors propose a principled approach for one-class SVMs (OC-SVM) that can be rewritten as distance/pooling neural networks, and apply deep Taylor decomposition (DTD), a methodology that leverages the model structure in order to quickly and reliably explain decisions in terms of input features.
Journal ArticleDOI
Enhancing the signal-to-noise ratio of ICA-based extracted ERPs
TL;DR: A method is developed that uses prior information about the phase-locking property of event-related potentials in a regularization framework to bias a blind source separation algorithm toward an improved separation of single-trial phase-locked responses in terms of an increased signal-to-noise ratio.
Proceedings Article
Adaptive On-line Learning in Changing Environments
TL;DR: An adaptive on-line algorithm extending the learning of learning idea can be applied to learning continuous functions or distributions, even when no explicit loss function is given and the Hessian is not available.
Journal ArticleDOI
A numerical study on learning curves in stochastic multilayer feedforward networks
TL;DR: It is shown for small t that the scaling law changes drastically, when the network undergoes a transition from strong overfitting to effective learning, and the asymptotic generalization error scales as 1/t as predicted.
Posted Content
Toward Interpretable Machine Learning: Transparent Deep Neural Networks and Beyond
Wojciech Samek,Grégoire Montavon,Sebastian Lapuschkin,Christopher J. Anders,Klaus-Robert Müller +4 more
TL;DR: This work aims to provide a timely overview of this active emerging field of machine learning and explain its theoretical foundations, put interpretability algorithms to a test both from a theory and comparative evaluation perspective using extensive simulations, and outline best practice aspects.