Klaus-Robert Müller

TL;DR: This study shows that the brain signals used for control can change substantially from the offline calibration sessions to online control, and also within a single session, and proposes several adaptive classification schemes and study their performance on data recorded during online experiments.

TL;DR: In this paper, a nonlinear form of principal component analysis (PCA) is proposed to perform polynomial feature extraction in high-dimensional feature spaces, related to input space by some nonlinear map; for instance, the space of all possible d-pixel products in images.

TL;DR: A general methodology based on region perturbation for evaluating ordered collections of pixels such as heatmaps and shows that the recently proposed layer-wise relevance propagation 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.

TL;DR: This chapter gives a concise introduction to LRP with a discussion of how to implement propagation rules easily and efficiently, how the propagation procedure can be theoretically justified as a ‘deep Taylor decomposition’, how to choose the propagation rules at each layer to deliver high explanation quality, and how LRP can be extended to handle a variety of machine learning scenarios beyond deep neural networks.

TL;DR: This paper describes efficient coding methods for video and depth data, and synthesis methods are presented, which mitigate errors from depth estimation and coding, for the generation of views.