scispace - formally typeset
Search or ask a question
Author

Klaus-Robert Müller

Other affiliations: Korea University, University of Tokyo, Fraunhofer Society  ...read more
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.


Papers
More filters
Proceedings Article
01 Jan 2000
TL;DR: It is found that both, KFD and the proposed sparse KFD, can be understood in an unifying probabilistic context and connections to Support Vector Machines and Relevance Vector Machines are shown.
Abstract: We investigate a new kernel-based classifier: the Kernel Fisher Discriminant (KFD). A mathematical programming formulation based on the observation that KFD maximizes the average margin permits an interesting modification of the original KFD algorithm yielding the sparse KFD. We find that both, KFD and the proposed sparse KFD, can be understood in an unifying probabilistic context. Furthermore, we show connections to Support Vector Machines and Relevance Vector Machines. From this understanding, we are able to outline an interesting kernel-regression technique based upon the KFD algorithm. Simulations support the usefulness of our approach.

189 citations

Proceedings ArticleDOI
19 Jul 2010
TL;DR: A depth image-based rendering (DIBR) approach with advanced inpainting methods with significant objective and subjective gains of the proposed method in comparison to the state-of-the-art methods is presented.
Abstract: In free viewpoint television or 3D video, depth image based rendering (DIBR) is used to generate virtual views based on a textured image and its associated depth information. In doing so, image regions which are occluded in the original view may become visible in the virtual image. One of the main challenges in DIBR is to extrapolate known textures into the disoccluded area without inserting subjective annoyance. In this paper, a new hole filling approach for DIBR using texture synthesis is presented. Initially, the depth map in the virtual view is filled at disoccluded locations. Then, in the textured image, holes of limited spatial extent are closed by solving Laplace equations. Larger disoccluded regions are initialized via median filtering and subsequently refined by patch-based texture synthesis. Experimental results show that the proposed approach provides improved rendering results in comparison to the latest MPEG view synthesis reference software (VSRS) version 3.6 [1].

186 citations

Journal ArticleDOI
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.
Abstract: Compensating changes between a subjects' training and testing session in brain-computer interfacing (BCI) is challenging but of great importance for a robust BCI operation. We show that such changes are very similar between subjects, and thus can be reliably estimated using data from other users and utilized to construct an invariant feature space. This novel approach to learning from other subjects aims to reduce the adverse effects of common nonstationarities, but does not transfer discriminative information. This is an important conceptual difference to standard multi-subject methods that, e.g., improve the covariance matrix estimation by shrinking it toward the average of other users or construct a global feature space. These methods do not reduces the shift between training and test data and may produce poor results when subjects have very different signal characteristics. In this paper, we compare our approach to two state-of-the-art multi-subject methods on toy data and two datasets of EEG recordings from subjects performing motor imagery. We show that it can not only achieve a significant increase in performance, but also that the extracted change patterns allow for a neurophysiologically meaningful interpretation.

184 citations

Journal ArticleDOI
TL;DR: The ability to achieve such high quality BMI control indicates that an SSVEP-based lower limb exoskeleton for gait assistance is becoming feasible, and the development of an asynchronous brain-machine interface (BMI), based on steady-state visual evoked potentials (SSVEPs).
Abstract: Objective. We have developed an asynchronous brain–machine interface (BMI)-based lower limb exoskeleton control system based on steady-state visual evoked potentials (SSVEPs). Approach. By decoding electroencephalography signals in real-time, users are able to walk forward, turn right, turn left, sit, and stand while wearing the exoskeleton. SSVEP stimulation is implemented with a visual stimulation unit, consisting of five light emitting diodes fixed to the exoskeleton. A canonical correlation analysis (CCA) method for the extraction of frequency information associated with the SSVEP was used in combination with k-nearest neighbors. Main results. Overall, 11 healthy subjects participated in the experiment to evaluate performance. To achieve the best classification, CCA was first calibrated in an offline experiment. In the subsequent online experiment, our results exhibit accuracies of 91.3 ± 5.73%, a response time of 3.28 ± 1.82 s, an information transfer rate of 32.9 ± 9.13 bits/min, and a completion time of 1100 ± 154.92 s for the experimental parcour studied. Significance. The ability to achieve such high quality BMI control indicates that an SSVEP-based lower limb exoskeleton for gait assistance is becoming feasible.

183 citations

Posted Content
TL;DR: It is shown that explanations can be manipulated arbitrarily by applying visually hardly perceptible perturbations to the input that keep the network's output approximately constant, and theoretically this phenomenon can be related to certain geometrical properties of neural networks.
Abstract: Explanation methods aim to make neural networks more trustworthy and interpretable. In this paper, we demonstrate a property of explanation methods which is disconcerting for both of these purposes. Namely, we show that explanations can be manipulated arbitrarily by applying visually hardly perceptible perturbations to the input that keep the network's output approximately constant. We establish theoretically that this phenomenon can be related to certain geometrical properties of neural networks. This allows us to derive an upper bound on the susceptibility of explanations to manipulations. Based on this result, we propose effective mechanisms to enhance the robustness of explanations.

180 citations


Cited by
More filters
Proceedings ArticleDOI
27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
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.

123,388 citations

Posted Content
TL;DR: This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
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.

44,703 citations

Book
18 Nov 2016
TL;DR: Deep learning as mentioned in this paper is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts, and it is used in many applications such as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames.
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.

38,208 citations

Journal ArticleDOI

[...]

08 Dec 2001-BMJ
TL;DR: There is, I think, something ethereal about i —the square root of minus one, which seems an odd beast at that time—an intruder hovering on the edge of reality.
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 …

33,785 citations

Proceedings Article
Sergey Ioffe1, Christian Szegedy1
06 Jul 2015
TL;DR: 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.
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.

30,843 citations