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.

The BCI competition 2003: progress and perspectives in detection and discrimination of EEG single trials

Abstract: Interest in developing a new method of man-to-machine communication-a brain-computer interface (BCI)-has grown steadily over the past few decades. BCIs create a new communication channel between the brain and an output device by bypassing conventional motor output pathways of nerves and muscles. These systems use signals recorded from the scalp, the surface of the cortex, or from inside the brain to enable users to control a variety of applications including simple word-processing software and orthotics. BCI technology could therefore provide a new communication and control option for individuals who cannot otherwise express their wishes to the outside world. Signal processing and classification methods are essential tools in the development of improved BCI technology. We organized the BCI Competition 2003 to evaluate the current state of the art of these tools. Four laboratories well versed in EEG-based BCI research provided six data sets in a documented format. We made these data sets (i.e., labeled training sets and unlabeled test sets) and their descriptions available on the Internet. The goal in the competition was to maximize the performance measure for the test labels. Researchers worldwide tested their algorithms and competed for the best classification results. This paper describes the six data sets and the results and function of the most successful algorithms.

Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space

Abstract: Simultaneously accurate and efficient prediction of molecular properties throughout chemical compound space is a critical ingredient toward rational compound design in chemical and pharmaceutical industries. Aiming toward this goal, we develop and apply a systematic hierarchy of efficient empirical methods to estimate atomization and total energies of molecules. These methods range from a simple sum over atoms, to addition of bond energies, to pairwise interatomic force fields, reaching to the more sophisticated machine learning approaches that are capable of describing collective interactions between many atoms or bonds. In the case of equilibrium molecular geometries, even simple pairwise force fields demonstrate prediction accuracy comparable to benchmark energies calculated using density functional theory with hybrid exchange-correlation functionals; however, accounting for the collective many-body interactions proves to be essential for approaching the “holy grail” of chemical accuracy of 1 kcal/mol ...

Efficient Prediction Structures for Multiview Video Coding

Abstract: An experimental analysis of multiview video coding (MVC) for various temporal and inter-view prediction structures is presented. The compression method is based on the multiple reference picture technique in the H.264/AVC video coding standard. The idea is to exploit the statistical dependencies from both temporal and inter-view reference pictures for motion-compensated prediction. The effectiveness of this approach is demonstrated by an experimental analysis of temporal versus inter-view prediction in terms of the Lagrange cost function. The results show that prediction with temporal reference pictures is highly efficient, but for 20% of a picture's blocks on average prediction with reference pictures from adjacent views is more efficient. Hierarchical B pictures are used as basic structure for temporal prediction. Their advantages are combined with inter-view prediction for different temporal hierarchy levels, starting from simulcast coding with no inter-view prediction up to full level inter-view prediction. When using inter-view prediction at key picture temporal levels, average gains of 1.4-dB peak signal-to-noise ratio (PSNR) are reported, while additionally using inter-view prediction at nonkey picture temporal levels, average gains of 1.6-dB PSNR are reported. For some cases, gains of more than 3 dB, corresponding to bit-rate savings of up to 50%, are obtained.

Robust and Communication-Efficient Federated Learning From Non-i.i.d. Data

Abstract: Federated learning allows multiple parties to jointly train a deep learning model on their combined data, without any of the participants having to reveal their local data to a centralized server. This form of privacy-preserving collaborative learning, however, comes at the cost of a significant communication overhead during training. To address this problem, several compression methods have been proposed in the distributed training literature that can reduce the amount of required communication by up to three orders of magnitude. These existing methods, however, are only of limited utility in the federated learning setting, as they either only compress the upstream communication from the clients to the server (leaving the downstream communication uncompressed) or only perform well under idealized conditions, such as i.i.d. distribution of the client data, which typically cannot be found in federated learning. In this article, we propose sparse ternary compression (STC), a new compression framework that is specifically designed to meet the requirements of the federated learning environment. STC extends the existing compression technique of top- $k$ gradient sparsification with a novel mechanism to enable downstream compression as well as ternarization and optimal Golomb encoding of the weight updates. Our experiments on four different learning tasks demonstrate that STC distinctively outperforms federated averaging in common federated learning scenarios. These results advocate for a paradigm shift in federated optimization toward high-frequency low-bitwidth communication, in particular in the bandwidth-constrained learning environments.

Unmasking Clever Hans Predictors and Assessing What Machines Really Learn

Abstract: Current learning machines have successfully solved hard application problems, reaching high accuracy and displaying seemingly "intelligent" behavior. Here we apply recent techniques for explaining decisions of state-of-the-art learning machines and analyze various tasks from computer vision and arcade games. This showcases a spectrum of problem-solving behaviors ranging from naive and short-sighted, to well-informed and strategic. We observe that standard performance evaluation metrics can be oblivious to distinguishing these diverse problem solving behaviors. Furthermore, we propose our semi-automated Spectral Relevance Analysis that provides a practically effective way of characterizing and validating the behavior of nonlinear learning machines. This helps to assess whether a learned model indeed delivers reliably for the problem that it was conceived for. Furthermore, our work intends to add a voice of caution to the ongoing excitement about machine intelligence and pledges to evaluate and judge some of these recent successes in a more nuanced manner.

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.