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.

Partial Optimality of Dual Decomposition for MAP Inference in Pairwise MRFs

Abstract: Markov random fields (MRFs) are a powerful tool for modelling statistical dependencies for a set of random variables using a graphical representation. An important computational problem related to MRFs, called maximum a posteriori (MAP) inference, is finding a joint variable assignment with the maximal probability. It is well known that the two popular optimisation techniques for this task, linear programming (LP) relaxation and dual decomposition (DD), have a strong connection both providing an optimal solution to the MAP problem when a corresponding LP relaxation is tight. However, less is known about their relationship in the opposite and more realistic case. In this paper, we explain how the fully integral assignments obtained via DD partially agree with the optimal fractional assignments via LP relaxation when the latter is not tight. In particular, for binary pairwise MRFs the corresponding result suggests that both methods share the partial optimality property of their solutions.

Higher order stationary subspace analysis

Abstract: Non-stationarity in data is an ubiquitous problem in signal processing. The recent stationary subspace analysis procedure (SSA) has enabled to decompose such data into a stationary subspace and a non-stationary part respectively. Algorithmically only weak non- stationarities could be tackled by SSA. The present paper takes the conceptual step generalizing from the use of first and second moments as in SSA to higher order moments, thus defining the proposed higher order stationary subspace analysis procedure (HOSSA). The paper derives the novel procedure and shows simulations. An obvious trade-off between the necessity of estimating higher moments and the accuracy and robustness with which they can be estimated is observed. In an ideal setting of plenty of data where higher moment information is dominating our novel approach can win against standard SSA. However, with limited data, even though higher moments actually dominate the underlying data, still SSA may arrive on par.

Rethinking BCI Paradigm and Machine Learning Algorithm as a Symbiosis: Zero Calibration, Guaranteed Convergence and High Decoding Performance.

Abstract: In the past, the decoding quality of brain-computer interface (BCI) systems was often enhanced by independently improving either the machine learning algorithms or the BCI paradigms. We propose to take a novel perspective instead by optimizing the whole system, paradigm and decoder, jointly. To exemplify this holistic idea, we introduce learning from label proportions (LLP) as a new classification approach and prove its value for visual event-related potential (ERP) signals of the EEG. LLP utilizes the existence of subgroups with different label proportions in the data. This leads to a conceptually simple BCI system which combines previously unseen capabilities: (1) it does not require calibration and learns from unlabeled data, (2) under i.i.d. conditions, LLP is guaranteed to obtain the optimal decoder for online data, (3) under violation of stationarity assumptions, LLP can continuously adapt to the changing data, and (4) it can, in practice, replace a traditional supervised decoder when combined with an expectation-maximization algorithm.

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.