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 Importance of Online Error Correction and Feed-Forward Adjustments in Brain-Machine Interfaces for Restoration of Movement

Abstract: Intended movement can now be decoded in real time from neural activity recorded via intracortical microelectrodes implanted in motor areas of the brain This opens up the possibility that severely paralyzed individuals may be able to use their extracted movement commands to control various assistive devices directly Even direct control of one's own paralyzed limbs may be possible by combining brain recording and decoding technologies with functional electrical stimulation systems that generate movement in paralyzed limbs by applying low levels of current to the peripheral nerves However, the microelectrode arrays can record only a small fraction of the neurons that normally are used to control movement, and we are unable to decode the user's desired movement without errors This chapter discusses experiments in which a monkey used its cortical signals to control the movements of a 3D cursor and a robotic arm in real time Both consistent errors and random errors were seen when decoding intended movement However, the animal learned to compensate for consistent decoding errors by making feed-forward adjustments to its motor plan The animal also learned to compensate for random decoding errors by using visual feedback to make online error corrections to the evolving movement trajectories This ability to compensate for imperfect decoding suggests intracortical signals may be quite useful for assistive device control even if the current technology does not perfectly extract the users native movement commands

Hidden Markov gating for prediction of change points in switching dynamical systems.

Abstract: The prediction of switching dynamical systems requires an identi cation of each individual dynamics and an early detection of mode changes. Here we present a uni ed framework of a mixtures of experts architecture and a generalized hidden Markov model (HMM) with a state space dependent transition matrix. The specialization of the experts in the dynamical regimes and the adaptation of the switching probabilities is performed simultaneously during the training procedure. We show that our method allows for a fast on{line detection of mode changes in cases where the most recent input data together with the last dynamical mode contain su cient information to indicate a dynamical change.

Discovering topics in text datasets by visualizing relevant words.

Abstract: When dealing with large collections of documents, it is imperative to quickly get an overview of the texts' contents. In this paper we show how this can be achieved by using a clustering algorithm to identify topics in the dataset and then selecting and visualizing relevant words, which distinguish a group of documents from the rest of the texts, to summarize the contents of the documents belonging to each topic. We demonstrate our approach by discovering trending topics in a collection of New York Times article snippets.

Obtaining the Best Linear Unbiased Estimator of Noisy Signals by Non-Gaussian Component Analysis

Abstract: Obtaining the best linear unbiased estimator (BLUE) of noisy signals is a traditional but powerful approach to noise reduction Explicitly computing BLUE usually requires the prior knowledge of the subspace to which the true signal belongs and the noise covariance matrix. However, such prior knowledge is often unavailable in reality, which prevents us from applying BLUE to real-world problems. In this paper, we therefore give a method for obtaining BLUE without such prior knowledge. Our additional assumption is that the true signal follows a non-Gaussian distribution while the noise is Gaussian.

Novel Paradigms for Auditory ERP Spellers with Spatial Hearing: Two Online Studies

Abstract: Two separate online studies with healthy subjects investigate the usability and the speed of novel Brain-Computer Interface paradigms that exclusively use spatial-auditory stimuli to drive an ERP speller. It was found that participants could use both paradigms (named AMUSE and PASS2D) for a spelling task with an average accuracy of over 85% and high speed (~0.9char/min). Based on these results, the paradigms qualify for future studies with patients, that suffer from a loss of gaze control.

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.