Klaus-Robert Müller

Bio: Klaus-Robert Müller is an academic researcher from Technical University of Berlin. The author has contributed to research in topics: Artificial neural network & Support vector machine. 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.

In Search of Non-Gaussian Components of a High-Dimensional Distribution

Abstract: Finding non-Gaussian components of high-dimensional data is an important preprocessing step for efficient information processing. This article proposes a new linear method to identify the "non-Gaussian subspace" within a very general semi-parametric framework. Our proposed method, called NGCA (non-Gaussian component analysis), is based on a linear operator which, to any arbitrary nonlinear (smooth) function, associates a vector belonging to the low dimensional non-Gaussian target subspace, up to an estimation error. By applying this operator to a family of different nonlinear functions, one obtains a family of different vectors lying in a vicinity of the target space. As a final step, the target space itself is estimated by applying PCA to this family of vectors. We show that this procedure is consistent in the sense that the estimaton error tends to zero at a parametric rate, uniformly over the family, Numerical examples demonstrate the usefulness of our method.

Explaining the unique nature of individual gait patterns with deep learning

Abstract: Machine learning (ML) techniques such as (deep) artificial neural networks (DNN) are solving very successfully a plethora of tasks and provide new predictive models for complex physical, chemical, biological and social systems. However, in most cases this comes with the disadvantage of acting as a black box, rarely providing information about what made them arrive at a particular prediction. This black box aspect of ML techniques can be problematic especially in medical diagnoses, so far hampering a clinical acceptance. The present paper studies the uniqueness of individual gait patterns in clinical biomechanics using DNNs. By attributing portions of the model predictions back to the input variables (ground reaction forces and full-body joint angles), the Layer-Wise Relevance Propagation (LRP) technique reliably demonstrates which variables at what time windows of the gait cycle are most relevant for the characterisation of gait patterns from a certain individual. By measuring the time-resolved contribution of each input variable to the prediction of ML techniques such as DNNs, our method describes the first general framework that enables to understand and interpret non-linear ML methods in (biomechanical) gait analysis and thereby supplies a powerful tool for analysis, diagnosis and treatment of human gait.

The Effect of Depth Compression on Multiview Rendering Quality

Abstract: This paper presents a comparative study on different techniques for depth-image compression and its implications on the quality of multiview video plus depth virtual view rendering. A novel coding algorithm for depth images that concentrates on their special characteristics, namely smooth regions delineated by sharp edges, is compared to H.264 intra-coding with depth- images. These two coding techniques are evaluated in the context of multiview video plus depth representations, where depth information is used to render virtual intermediate camera views of the scene. Therefore it is important to evaluate the influence of depth-image coding artifacts on the quality of rendered virtual views. The results of this evaluation show, that the coding algorithm specialized on the characteristics of depth images outperforms H.264 intra-coding, although its RD-performance is worse.

Multivariate Machine Learning Methods for Fusing Multimodal Functional Neuroimaging Data

Abstract: Multimodal data are ubiquitous in engineering, communications, robotics, computer vision, or more generally speaking in industry and the sciences. All disciplines have developed their respective sets of analytic tools to fuse the information that is available in all measured modalities. In this paper, we provide a review of classical as well as recent machine learning methods (specifically factor models) for fusing information from functional neuroimaging techniques such as: LFP, EEG, MEG, fNIRS, and fMRI. Early and late fusion scenarios are distinguished, and appropriate factor models for the respective scenarios are presented along with example applications from selected multimodal neuroimaging studies. Further emphasis is given to the interpretability of the resulting model parameters, in particular by highlighting how factor models relate to physical models needed for source localization. The methods we discuss allow for the extraction of information from neural data, which ultimately contributes to 1) better neuroscientific understanding; 2) enhance diagnostic performance; and 3) discover neural signals of interest that correlate maximally with a given cognitive paradigm. While we clearly study the multimodal functional neuroimaging challenge, the discussed machine learning techniques have a wide applicability, i.e., in general data fusion, and may thus be informative to the general interested reader.

Temporally consistent handling of disocclusions with texture synthesis for depth-image-based rendering

Abstract: Depth-image-based rendering (DIBR) is used to generate additional views of a real-world scene from images or videos and associated per-pixel depth information. An inherent problem of the view synthesis concept is the fact that image information which is occluded in the original view may become visible in the “virtual” image. The resulting question is: how can these disocclusions be covered in a visually plausible manner? In this paper, a new temporally and spatially consistent hole filling method for DIBR is presented. In a first step, disocclusions in the depth map are filled. Then, a background sprite is generated and updated with every frame using the original and synthesized information from previous frames to achieve temporally consistent results. Next, small holes resulting from depth estimation inaccuracies are closed in the textured image, using methods that are based on solving Laplace equations. The residual disoccluded areas are coarsely initialized and subsequently refined by patch-based texture synthesis. Experimental results are presented, highlighting that gains in objective and visual quality can be achieved in comparison to the latest MPEG view synthesis reference software (VSRS).

Deep Residual Learning for Image Recognition

Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

Deep Residual Learning for Image Recognition

Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers---8x deeper than VGG nets but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

Deep Learning

Abstract: Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

I and i

Abstract: There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality. Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Abstract: Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates and careful parameter initialization, and makes it notoriously hard to train models with saturating nonlinearities. We refer to this phenomenon as internal covariate shift, and address the problem by normalizing layer inputs. Our method draws its strength from making normalization a part of the model architecture and performing the normalization for each training mini-batch. Batch Normalization allows us to use much higher learning rates and be less careful about initialization, and in some cases eliminates the need for Dropout. Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin. Using an ensemble of batch-normalized networks, we improve upon the best published result on ImageNet classification: reaching 4.82% top-5 test error, exceeding the accuracy of human raters.