Showing papers by "Klaus-Robert Müller published in 2015"

On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation.

Abstract: Understanding and interpreting classification decisions of automated image classification systems is of high value in many applications, as it allows to verify the reasoning of the system and provides additional information to the human expert. Although machine learning methods are solving very successfully a plethora of tasks, they have in most cases the disadvantage of acting as a black box, not providing any information about what made them arrive at a particular decision. This work proposes a general solution to the problem of understanding classification decisions by pixel-wise decomposition of nonlinear classifiers. We introduce a methodology that allows to visualize the contributions of single pixels to predictions for kernel-based classifiers over Bag of Words features and for multilayered neural networks. These pixel contributions can be visualized as heatmaps and are provided to a human expert who can intuitively not only verify the validity of the classification decision, but also focus further analysis on regions of potential interest. We evaluate our method for classifiers trained on PASCAL VOC 2009 images, synthetic image data containing geometric shapes, the MNIST handwritten digits data set and for the pre-trained ImageNet model available as part of the Caffe open source package.

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 ...

Evaluating the visualization of what a Deep Neural Network has learned

Abstract: Deep Neural Networks (DNNs) have demonstrated impressive performance in complex machine learning tasks such as image classification or speech recognition. However, due to their multi-layer nonlinear structure, they are not transparent, i.e., it is hard to grasp what makes them arrive at a particular classification or recognition decision given a new unseen data sample. Recently, several approaches have been proposed enabling one to understand and interpret the reasoning embodied in a DNN for a single test image. These methods quantify the ''importance'' of individual pixels wrt the classification decision and allow a visualization in terms of a heatmap in pixel/input space. While the usefulness of heatmaps can be judged subjectively by a human, an objective quality measure is missing. In this paper we present a general methodology based on region perturbation for evaluating ordered collections of pixels such as heatmaps. We compare heatmaps computed by three different methods on the SUN397, ILSVRC2012 and MIT Places data sets. Our main result is that the recently proposed Layer-wise Relevance Propagation (LRP) algorithm qualitatively and quantitatively provides a better explanation of what made a DNN arrive at a particular classification decision than the sensitivity-based approach or the deconvolution method. We provide theoretical arguments to explain this result and discuss its practical implications. Finally, we investigate the use of heatmaps for unsupervised assessment of neural network performance.

On the influence of high-pass filtering on ICA-based artifact reduction in EEG-ERP

Abstract: Standard artifact removal methods for electroencephalographic (EEG) signals are either based on Independent Component Analysis (ICA) or they regress out ocular activity measured at electrooculogram (EOG) channels. Successful ICA-based artifact reduction relies on suitable pre-processing. Here we systematically evaluate the effects of high-pass filtering at different frequencies. Offline analyses were based on event-related potential data from 21 participants performing a standard auditory oddball task and an automatic artifactual component classifier method (MARA). As a pre-processing step for ICA, high-pass filtering between 1–2 Hz consistently produced good results in terms of signal-to-noise ratio (SNR), single-trial classification accuracy and the percentage of ‘near-dipolar’ ICA components. Relative to no artifact reduction, ICA-based artifact removal significantly improved SNR and classification accuracy. This was not the case for a regression-based approach to remove EOG artifacts.

A lower limb exoskeleton control system based on steady state visual evoked potentials.

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.

Towards Noninvasive Hybrid Brain–Computer Interfaces: Framework, Practice, Clinical Application, and Beyond

Abstract: In their early days, brain–computer interfaces (BCIs) were only considered as control channel for end users with severe motor impairments such as people in the locked-in state. But, thanks to the multidisciplinary progress achieved over the last decade, the range of BCI applications has been substantially enlarged. Indeed, today BCI technology cannot only translate brain signals directly into control signals, but also can combine such kind of artificial output with a natural muscle-based output. Thus, the integration of multiple biological signals for real-time interaction holds the promise to enhance a much larger population than originally thought end users with preserved residual functions who could benefit from new generations of assistive technologies. A BCI system that combines a BCI with other physiological or technical signals is known as hybrid BCI (hBCI). In this work, we review the work of a large scale integrated project funded by the European commission which was dedicated to develop practical hybrid BCIs and introduce them in various fields of applications. This article presents an hBCI framework, which was used in studies with nonimpaired as well as end users with motor impairments.

Analyzing Classifiers: Fisher Vectors and Deep Neural Networks

Abstract: Fisher Vector classifiers and Deep Neural Networks (DNNs) are popular and successful algorithms for solving image classification problems. However, both are generally considered `black box' predictors as the non-linear transformations involved have so far prevented transparent and interpretable reasoning. Recently, a principled technique, Layer-wise Relevance Propagation (LRP), has been developed in order to better comprehend the inherent structured reasoning of complex nonlinear classification models such as Bag of Feature models or DNNs. In this paper we (1) extend the LRP framework also for Fisher Vector classifiers and then use it as analysis tool to (2) quantify the importance of context for classification, (3) qualitatively compare DNNs against FV classifiers in terms of important image regions and (4) detect potential flaws and biases in data. All experiments are performed on the PASCAL VOC 2007 data set.

Understanding kernel ridge regression: Common behaviors from simple functions to density functionals

Abstract: Accurate approximations to density functionals have recently been obtained via machine learning (ML). By applying ML to a simple function of one variable without any random sampling, we extract the qualitative dependence of errors on hyperparameters. We find universal features of the behavior in extreme limits, including both very small and very large length scales, and the noise-free limit. We show how such features arise in ML models of density functionals. © 2015 Wiley Periodicals, Inc.

Learning From More Than One Data Source: Data Fusion Techniques for Sensorimotor Rhythm-Based Brain–Computer Interfaces

Abstract: Brain–computer interfaces (BCIs) are successfully used in scientific, therapeutic and other applications. Remaining challenges are among others a low signal-to-noise ratio of neural signals, lack of robustness for decoders in the presence of inter-trial and inter-subject variability, time constraints on the calibration phase and the use of BCIs outside a controlled lab environment. Recent advances in BCI research addressed these issues by novel combinations of complementary analysis as well as recording techniques, so called hybrid BCIs . In this paper, we review a number of data fusion techniques for BCI along with hybrid methods for BCI that have recently emerged. Our focus will be on sensorimotor rhythm-based BCIs. We will give an overview of the three main lines of research in this area, integration of complementary features of neural activation, integration of multiple previous sessions and of multiple subjects, and show how these techniques can be used to enhance modern BCI systems.

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.

Concurrent Adaptation of Human and Machine Improves Simultaneous and Proportional Myoelectric Control

Abstract: Myoelectric control of a prosthetic hand with more than one degree of freedom (DoF) is challenging, and clinically available techniques require a sequential actuation of the DoFs. Simultaneous and proportional control of multiple DoFs is possible with regression-based approaches allowing for fluent and natural movements. Conventionally, the regressor is calibrated in an open-loop with training based on recorded data and the performance is evaluated subsequently. For individuals with amputation or congenital limb-deficiency who need to (re)learn how to generate suitable muscle contractions, this open-loop process may not be effective. We present a closed-loop real-time learning scheme in which both the user and the machine learn simultaneously to follow a common target. Experiments with ten able-bodied individuals show that this co-adaptive closed-loop learning strategy leads to significant performance improvements compared to a conventional open-loop training paradigm. Importantly, co-adaptive learning allowed two individuals with congenital deficiencies to perform simultaneous 2-D proportional control at levels comparable to the able-bodied individuals, despite having to a learn completely new and unfamiliar mapping from muscle activity to movement trajectories. To our knowledge, this is the first study which investigates man-machine co-adaptation for regression-based myoelectric control. The proposed training strategy has the potential to improve myographic prosthetic control in clinically relevant settings.

EEG-based classification of video quality perception using steady state visual evoked potentials (SSVEPs).

Abstract: Objective. Recent studies exploit the neural signal recorded via electroencephalography (EEG) to get a more objective measurement of perceived video quality. Most of these studies capitalize on the event-related potential component P3. We follow an alternative approach to the measurement problem investigating steady state visual evoked potentials (SSVEPs) as EEG correlates of quality changes. Unlike the P3, SSVEPs are directly linked to the sensory processing of the stimuli and do not require long experimental sessions to get a sufficient signal-to-noise ratio. Furthermore, we investigate the correlation of the EEG-based measures with the outcome of the standard behavioral assessment. Approach. As stimulus material, we used six gray-level natural images in six levels of degradation that were created by coding the images with the HM10.0 test model of the high efficiency video coding (H.265/MPEG-HEVC) using six different compression rates. The degraded images were presented in rapid alternation with the original images. In this setting, the presence of SSVEPs is a neural marker that objectively indicates the neural processing of the quality changes that are induced by the video coding. We tested two different machine learning methods to classify such potentials based on the modulation of the brain rhythm and on time-locked components, respectively. Main results. Results show high accuracies in classification of the neural signal over the threshold of the perception of the quality changes. Accuracies significantly correlate with the mean opinion scores given by the participants in the standardized degradation category rating quality assessment of the same group of images. Significance. The results show that neural assessment of video quality based on SSVEPs is a viable complement of the behavioral one and a significantly fast alternative to methods based on the P3 component.

Nonlinear gradient denoising: Finding accurate extrema from inaccurate functional derivatives

Abstract: A method for nonlinear optimization with machine learning (ML) models, called nonlinear gradient denoising (NLGD), is developed, and applied with ML approximations to the kinetic energy density functional in an orbital-free density functional theory. Due to systematically inaccurate gradients of ML models, in particular when the data is very high-dimensional, the optimization must be constrained to the data manifold. We use nonlinear kernel principal component analysis (PCA) to locally reconstruct the manifold, enabling a projected gradient descent along it. A thorough analysis of the method is given via a simple model, designed to clarify the concepts presented. Additionally, NLGD is compared with the local PCA method used in previous work. Our method is shown to be superior in cases when the data manifold is highly nonlinear and high dimensional. Further applications of the method in both density functional theory and ML are discussed. © 2015 Wiley Periodicals, Inc.

Relevance score assignment for artificial neural networks

Abstract: The task of relevance score assignment to a set of items onto which an artificial neural network is applied is obtained by redistributing an initial relevance score derived from the network output, onto the set of items by reversely propagating the initial relevance score through the artificial neural network so as to obtain a relevance score for each item. In particular, this reverse propagation is applicable to a broader set of artificial neural networks and/or at lower computational efforts by performing same in a manner so that for each neuron, preliminarily redistributed relevance scores of a set of downstream neighbor neurons of the respective neuron are distributed on a set of upstream neighbor neurons of the respective neuron according to a distribution function.

Distributed functions of detection and discrimination of vibrotactile stimuli in the hierarchical human somatosensory system.

Abstract: According to the hierarchical view of human somatosensory network, somatic sensory information is relayed from the thalamus to primary somatosensory cortex (S1), and then distributed to adjacent cortical regions to perform further perceptual and cognitive functions Although a number of neuroimaging studies have examined neuronal activity correlated with tactile stimuli, comparatively less attention has been devoted toward understanding how vibrotactile stimulus information is processed in the hierarchical somatosensory cortical network To explore the hierarchical perspective of tactile information processing, we studied two cases: (a) discrimination between the locations of finger stimulation, and (b) detection of stimulation against no stimulation on individual fingers, using both standard general linear model (GLM) and searchlight multi-voxel pattern analysis (MVPA) techniques These two cases were studied on the same data set resulting from a passive vibrotactile stimulation experiment Our results showed that vibrotactile stimulus locations on fingers could be discriminated from measurements of human functional magnetic resonance imaging (fMRI) In particular, it was in case (a) where we observed activity in contralateral posterior parietal cortex (PPC) and supramarginal gyrus (SMG) but not in S1, while in case (b) we found significant cortical activations in S1 but not in PPC and SMG These discrepant observations suggest the functional specialization with regard to vibrotactile stimulus locations, especially, the hierarchical information processing in the human somatosensory cortical areas Our findings moreover support the general understanding that S1 is the main sensory receptive area for the sense of touch, and adjacent cortical regions (ie, PPC and SMG) are in charge of a higher level of processing and may thus contribute most for the successful classification between stimulated finger locations

Neurophysiological assessment of perceived image quality using steady-state visual evoked potentials

Abstract: An approach to the neural measurement of perceived image quality using electroencephalography (EEG) is presented. 6 different images were tested on 6 different distortion levels. The distortions were introduced by a hybrid video encoder. The presented study consists of two parts: In a first part, subjects were asked to evaluate the quality of the test stimuli behaviorally during a conventional psychophysical test using a degradation category rating procedure. In a second part, subjects were presented undistorted and distorted texture images in a periodically alternating fashion at a fixed frequency. This alternating presentation elicits so called steady-state visual evoked potentials (SSVEP) as a brain response that can be measured on the scalp. The amplitude of modulations in the brain signals is significantly and strongly negatively correlated with the magnitude of visual impairment reported by the subjects. This neurophysiological approach to image quality assessment may potentially lead to a more objective evaluation, as behavioral approaches suffer from drawbacks such as biases, inter-subject variances and limitations to test duration.

Bringing BCI into everyday life: Motor imagery in a pseudo realistic environment

Abstract: Bringing Brain-Computer Interfaces (BCIs) into everyday life is a challenge because an out-of-lab environment implies the presence of variables that are largely beyond control of the user and the software application. This can severely corrupt signal quality as well as reliability of BCI control. Current BCI technology may fail in this application scenario because of the large amounts of noise, nonstationarity and movement artifacts. In this paper, we systematically investigate the performance of motor imagery BCI in a pseudo realistic environment. In our study 16 participants were asked to perform motor imagery tasks while dealing with different types of distractions such as vibratory stimulations or listening tasks. Our experiments demonstrate that standard BCI procedures are not robust to theses additional sources of noise, implicating that methods which work well in a lab environment, may perform poorly in realistic application scenarios. We discuss several promising research directions to tackle this important problem.

Opening the Black Box: revealing interpretable sequence motifs in kernel-based learning algorithms

Abstract: This work is in the context of kernel-based learning algorithms for sequence data. We present a probabilistic approach to automatically extract, from the output of such string-kernel-based learning algorithms, the subsequences--or motifs--truly underlying the machine's predictions. The proposed framework views motifs as free parameters in a probabilistic model, which is solved through a global optimization approach. In contrast to prevalent approaches, the proposed method can discover even difficult, long motifs, and could be combined with any kernel-based learning algorithm that is based on an adequate sequence kernel. We show that, by using a discriminate kernel machine such as a support vector machine, the approach can reveal discriminative motifs underlying the kernel predictor. We demonstrate the efficacy of our approach through a series of experiments on synthetic and real data, including problems from handwritten digit recognition and a large-scale human splice site data set from the domain of computational biology.

Wasserstein Training of Boltzmann Machines

Abstract: The Boltzmann machine provides a useful framework to learn highly complex, multimodal and multiscale data distributions that occur in the real world. The default method to learn its parameters consists of minimizing the Kullback-Leibler (KL) divergence from training samples to the Boltzmann model. We propose in this work a novel approach for Boltzmann training which assumes that a meaningful metric between observations is given. This metric can be represented by the Wasserstein distance between distributions, for which we derive a gradient with respect to the model parameters. Minimization of this new Wasserstein objective leads to generative models that are better when considering the metric and that have a cluster-like structure. We demonstrate the practical potential of these models for data completion and denoising, for which the metric between observations plays a crucial role.

Classifying directions in continuous arm movement from EEG signals

Abstract: EEG based upper limb rehabilitation has limitation on the control commands of neuro-prosthetics cannot deal with human's real movements. To resolve this problem, it is important to know about neural correlation of the directions of arm movement. Previous studies classified the directions of arm movement, using center-out task, only including y-z-axis movement. In this research, 4 subjects participated in experiment and the movement of their right arm in infinity shape (∞) divided into six part of symbol. Moreover, we used Common Spatial Pattern (CSP) algorithm to extract finer feature of EEG signal and Linear Discriminant Analysis (LDA) method to classify directions of movement. The result states that, average of classification accuracy was 74% and standard derivation was 0.08. In the topographical map at the center of infinity shape, we could observe the divided image of left and right side of the brain and FC3, F7 and C3 channels included most information about directions of movement. By the result of this study, we can confirm the possibility of controlling neuro-prosthetics and evidence of neurological basis of the arm movement.

Investigating effects of different artefact types on motor imagery BCI

Abstract: Artefacts in recordings of the electroencephalogram (EEG) are a common problem in Brain-Computer Interfaces (BCIs). Artefacts make it difficult to calibrate from training sessions, resulting in low test performance, or lead to artificially high performance when unintentionally used for BCI control. We investigate different artefacts' effects on motor-imagery based BCI relying on Common Spatial Patterns (CSP). Data stem from an 80-subject BCI study. We use the recently developed classifier IC_MARC to classify independent components of EEG data into neural and five classes of artefacts. We find that muscle, but not ocular, artefacts adversely affect BCI performance when all 119 EEG channels are used. Artefacts have little influence when using 48 centrally located EEG channels in a configuration previously found to be optimal.

The need for novel informatics tools for integrating and planning research in molecular and cellular cognition

Abstract: The sheer volume and complexity of publications in the biological sciences are straining traditional approaches to research planning. Nowhere is this problem more serious than in molecular and cellular cognition, since in this neuroscience field, researchers routinely use approaches and information from a variety of areas in neuroscience and other biology fields. Additionally, the multilevel integration process characteristic of this field involves the establishment of experimental connections between molecular, electrophysiological, behavioral, and even cognitive data. This multidisciplinary integration process requires strategies and approaches that originate in several different fields, which greatly increases the complexity and demands of this process. Although causal assertions, where phenomenon A is thought to contribute or relate to B, are at the center of this integration process and key to research in biology, there are currently no tools to help scientists keep track of the increasingly more complex network of causal connections they use when making research decisions. Here, we propose the development of semiautomated graphical and interactive tools to help neuroscientists and other biologists, including those working in molecular and cellular cognition, to track, map, and weight causal evidence in research papers. There is a great need for a concerted effort by biologists, computer scientists, and funding institutions to develop maps of causal information that would aid in integration of research findings and in experiment planning.

SVM2Motif—Reconstructing Overlapping DNA Sequence Motifs by Mimicking an SVM Predictor

Abstract: Identifying discriminative motifs underlying the functionality and evolution of organisms is a major challenge in computational biology. Machine learning approaches such as support vector machines (SVMs) achieve state-of-the-art performances in genomic discrimination tasks, but--due to its black-box character--motifs underlying its decision function are largely unknown. As a remedy, positional oligomer importance matrices (POIMs) allow us to visualize the significance of position-specific subsequences. Although being a major step towards the explanation of trained SVM models, they suffer from the fact that their size grows exponentially in the length of the motif, which renders their manual inspection feasible only for comparably small motif sizes, typically k ≤ 5. In this work, we extend the work on positional oligomer importance matrices, by presenting a new machine-learning methodology, entitled motifPOIM, to extract the truly relevant motifs--regardless of their length and complexity--underlying the predictions of a trained SVM model. Our framework thereby considers the motifs as free parameters in a probabilistic model, a task which can be phrased as a non-convex optimization problem. The exponential dependence of the POIM size on the oligomer length poses a major numerical challenge, which we address by an efficient optimization framework that allows us to find possibly overlapping motifs consisting of up to hundreds of nucleotides. We demonstrate the efficacy of our approach on a synthetic data set as well as a real-world human splice site data set.

Robust common spatial patterns based on Bhattacharyya distance and Gamma divergence

Abstract: The computation of task-related spatial filters is a prerequisite for a successful application of motor imagery-based Brain-Computer Interfaces (BCI). However, in the presence of artifacts, e.g., resulting from eye movements or muscular activity, standard methods such as Common Spatial Patterns (CSP) perform poorly. Recently, a divergence-based spatial filter computation framework has been proposed which enables significantly more robust computation with respect to artifacts by using Beta divergence. In this paper we integrate two additional divergence measures, namely Bhattacharyya distance and Gamma divergence, into the divergence-based CSP framework and evaluate their robustness using simulations and data set IVa from BCI Competition III.

Three-way analysis of spectrospatial electromyography data: classification and interpretation.

Abstract: Classifying multivariate electromyography (EMG) data is an important problem in prosthesis control as well as in neurophysiological studies and diagnosis. With modern high-density EMG sensor technology, it is possible to capture the rich spectrospatial structure of the myoelectric activity. We hypothesize that multi-way machine learning methods can efficiently utilize this structure in classification as well as reveal interesting patterns in it. To this end, we investigate the suitability of existing three-way classification methods to EMG-based hand movement classification in spectrospatial domain, as well as extend these methods by sparsification and regularization. We propose to use Fourier-domain independent component analysis as preprocessing to improve classification and interpretability of the results. In high-density EMG experiments on hand movements across 10 subjects, three-way classification yielded higher average performance compared with state-of-the art classification based on temporal features, suggesting that the three-way analysis approach can efficiently utilize detailed spectrospatial information of high-density EMG. Phase and amplitude patterns of features selected by the classifier in finger-movement data were found to be consistent with known physiology. Thus, our approach can accurately resolve hand and finger movements on the basis of detailed spectrospatial information, and at the same time allows for physiological interpretation of the results.

Tackling noise, artifacts and nonstationarity in BCI with robust divergences

Abstract: Although the field of Brain-Computer Interfacing (BCI) has made incredible advances in the last decade, current BCIs are still scarcely used outside laboratories. One reason is the lack of robustness to noise, artifacts and nonstationarity which are intrinsic parts of the recorded brain signal. Furthermore out-of-lab environments imply the presence of external variables that are largely beyond the control of the user, but can severely corrupt signal quality. This paper presents a new generation of robust EEG signal processing approaches based on the information geometric notion of divergence. We show that these divergence-based methods can be used for robust spatial filtering and thus increase the systems' reliability when confronted to, e.g., environmental noise, users' motions or electrode artifacts. Furthermore we extend the divergence-based framework to heavy-tail distributions and investigate the advantages of a joint optimization for robustness and stationarity.

Recent Progress in Brain and Cognitive Engineering

Abstract: Part I. Non-invasive Brain-Computer Interface.- Chapter 1. Future directions for brain-machine interfacing technology.- Chapter 2. Brain-Computer Interface for Smart Vehicle: Detection of Braking Intention during Simulated Driving.- Chapter 3. Benefits and limits of multimodal neuroimaging for Brain Computer Interfaces.- Chapter 4. Multifrequency Analysis of Brain-Computer Interfaces.- Part II. Cognitive- and Neural-rehabilitation Engineering.- Chapter 5. Current Trends in Memory Implantation and Rehabilitation.- Chapter 6. Moving Brain Controlled Devices Outside the Lab: Principles and Applications.- Part III. Big Data Neurocomputing.- Chapter 7. Across cultures: a Cognitive and Computational Analysis of Emotional and Conversational Facial Expressions in Germany and Korea.- Chapter 8. Bottom-Up Processing in Complex Scenes: a unifying perspective on segmentation, fixation saliency, candidate regions, base-detail decomposition, and image enhancement.- Chapter 9. Perception-based motion cueing: a Cybernetics approach to motion simulation.- Chapter 10. The other-race effect revisited: no effect for faces varying in race only.- Part IV. Early Diagnosis and Prediction of Neural Diseases.- Chapter 11. Functional neuromonitoring in acquired head injury.- Chapter 12. Diagnostic Optical Imaging Technology and its Principles.- Chapter 13. Detection of Brain Metastases using Magnetic Resonance Imaging.- Chapter 14. Deep Learning in Diagnosis of Brain Disorders.