Moritz Grosse-Wentrup

Max-Planck-Institut für Intelligente Systeme, Tübingen, Tübingen, Baden-Württemberg, Germany

Are you Moritz Grosse-Wentrup?

Claim your profile

Publications (52)98.81 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: It is often a problem in various fields that one runs into a series of tasks that appear - to a human - to be highly related to each other, yet applying the optimal machine learning solution of one problem to another results in poor performance. Specifically in the field of brain-computer interfaces (BCIs), it has long been known that a subject with good classification of some brain signal today could come into the experimental setup tomorrow and perform terribly using the exact same classifier. One initial approach to get over this problem was to fix the classification rule beforehand and train the patient to force brain activity to conform to this rule.
    No preview · Article · Feb 2016 · IEEE Computational Intelligence Magazine
  • Sebastian Weichwald · Moritz Grosse-Wentrup · Arthur Gretton
    [Show abstract] [Hide abstract]
    ABSTRACT: Causal inference concerns the identification of cause-effect relationships between variables. However, often only a linear combination of variables constitutes a meaningful causal variable. We propose to construct causal variables from non-causal variables such that the resulting statistical properties guarantee meaningful cause-effect relationships. Exploiting this novel idea, MERLiN is able to recover a causal variable from an observed linear mixture that is an effect of another given variable. We illustrate how to adapt the algorithm to a particular domain and how to incorporate a priori knowledge. Evaluation on both synthetic and experimental EEG data indicates MERLiN's power to infer cause-effect relationships.
    No preview · Article · Dec 2015
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The performance of brain-computer interfaces (BCIs) improves with the amount of available training data, the statistical distribution of this data, however, varies across subjects as well as across sessions within individual subjects, limiting the transferability of training data or trained models between them. In this article, we review current transfer learning techniques in BCIs that exploit shared structure between training data of multiple subjects and/or sessions to increase performance. We then present a framework for transfer learning in the context of BCIs that can be applied to any arbitrary feature space, as well as a novel regression estimation method that is specifically designed for the structure of a system based on the electroencephalogram (EEG). We demonstrate the utility of our framework and method on subject-to-subject transfer in a motor-imagery paradigm as well as on session-to-session transfer in one patient diagnosed with amyotrophic lateral sclerosis (ALS), showing that it is able to outperform other comparable methods on an identical dataset.
    Preview · Article · Dec 2015
  • Source
    Moritz Grosse-Wentrup · Dominik Janzing · Markus Siegel · Bernhard Schölkopf
    [Show abstract] [Hide abstract]
    ABSTRACT: We consider the task of inferring causal relations in brain imaging data with latent confounders. Using a priori knowledge that randomized experimental conditions can not be effects of brain activity, we derive statistical conditions that are sufficientfor establishing a causal relation between two neural processes, even in the presence of latent confounders. We provide an algorithm to test these conditions on empirical data, and illustrate its performance on simulated as well as on experimentally recorded EEG data.
    Full-text · Article · Oct 2015 · NeuroImage
  • O. Özdenizci · T. Meyer · M. Çetin · M. Grosse-Wentrup
    [Show abstract] [Hide abstract]
    ABSTRACT: Numerous electroencephalogram (EEG) based Brain-Computer Interface (BCI) systems are being used as alternative means of communication for locked-in patients. Beyond these, BCIs are also considered in the context of post-stroke motor rehabilitation. Such research usually focuses on exploiting information decoded from sensorimotor activity of the brain. Here, we propose to extend this current focus beyond sensorimotor to also include associative brain areas. In this pilot study, we present an adaptive neurofeedback training paradigm to up-regulate particular EEG activity that is likely to enhance post-stroke motor rehabilitation. Our experimental results support the interpretation that the neurofeedback paradigm enables subjects to up-regulate intended activity and sustain that modulation in inter-trial resting periods in a state that we believe can support motor learning performance. These results serve as a beginning on viability of our claim on integrating a neurofeedback approach to BCI-based motor rehabilitation protocols.
    No preview · Article · Jun 2015
  • [Show abstract] [Hide abstract]
    ABSTRACT: Causal terminology is often introduced in the interpretation of encoding and decoding models trained on neuroimaging data. In this article, we investigate which causal statements are warranted and which ones are not supported by empirical evidence. We argue that the distinction between encoding and decoding models is not sufficient for this purpose: relevant features in encoding and decoding models carry a different meaning in stimulus- and in response-based experimental paradigms.We show that only encoding models in the stimulus-based setting support unambiguous causal interpretations. By combining encoding and decoding models trained on the same data, however, we obtain insights into causal relations beyond those that are implied by each individual model type. We illustrate the empirical relevance of our theoretical findings on EEG data recorded during a visuo-motor learning task. Copyright © 2015. Published by Elsevier Inc.
    No preview · Article · Jan 2015 · NeuroImage
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disease with substantial heterogeneity in its clinical presentation. This makes diagnosis and effective treatment difficult, so better tools for estimating disease progression are needed. Here, we report results from the DREAM-Phil Bowen ALS Prediction Prize4Life challenge. In this crowdsourcing competition, competitors developed algorithms for the prediction of disease progression of 1,822 ALS patients from standardized, anonymized phase 2/3 clinical trials. The two best algorithms outperformed a method designed by the challenge organizers as well as predictions by ALS clinicians. We estimate that using both winning algorithms in future trial designs could reduce the required number of patients by at least 20%. The DREAM-Phil Bowen ALS Prediction Prize4Life challenge also identified several potential nonstandard predictors of disease progression including uric acid, creatinine and surprisingly, blood pressure, shedding light on ALS pathobiology. This analysis reveals the potential of a crowdsourcing competition that uses clinical trial data for accelerating ALS research and development.
    Preview · Article · Nov 2014 · Nature Biotechnology
  • Source
    Pouyan R. Fard · Moritz Grosse-Wentrup
    [Show abstract] [Hide abstract]
    ABSTRACT: Understanding the relationship between the decoding accuracy of a brain-computer interface (BCI) and a subject's subjective feeling of control is important for determining a lower limit on decoding accuracy for a BCI that is to be deployed outside a laboratory environment. We investigated this relationship by systematically varying the level of control in a simulated BCI task. We find that a binary decoding accuracy of 65% is required for users to report more often than not that they are feeling in control of the system. Decoding accuracies above 75%, on the other hand, added little in terms of the level of perceived control. We further find that the probability of perceived control does not only depend on the actual decoding accuracy, but is also in influenced by whether subjects successfully complete the given task in the allotted time frame.
    Full-text · Article · Oct 2014
  • Moritz Grosse-Wentrup · Bernhard Schölkopf
    [Show abstract] [Hide abstract]
    ABSTRACT: Objective: Brain-computer interface (BCI) systems are often based on motor- and/or sensory processes that are known to be impaired in late stages of amyotrophic lateral sclerosis (ALS). We propose a novel BCI designed for patients in late stages of ALS that only requires high-level cognitive processes to transmit information from the user to the BCI. Approach: We trained subjects via EEG-based neurofeedback to self-regulate the amplitude of gamma-oscillations in the superior parietal cortex (SPC). We argue that parietal gamma-oscillations are likely to be associated with high-level attentional processes, thereby providing a communication channel that does not rely on the integrity of sensory- and/or motor-pathways impaired in late stages of ALS. Main results: Healthy subjects quickly learned to self-regulate gamma-power in the SPC by alternating between states of focused attention and relaxed wakefulness, resulting in an average decoding accuracy of 70.2%. One locked-in ALS patient (ALS-FRS-R score of zero) achieved an average decoding accuracy significantly above chance-level though insufficient for communication (55.8%). Significance: Self-regulation of gamma-power in the SPC is a feasible paradigm for brain-computer interfacing and may be preserved in late stages of ALS. This provides a novel approach to testing whether completely locked-in ALS patients retain the capacity for goal-directed thinking.
    No preview · Article · Aug 2014 · Journal of Neural Engineering
  • Sebastian Weichwald · Bernhard Scholkopf · Tonio Ball · Moritz Grosse-Wentrup
    [Show abstract] [Hide abstract]
    ABSTRACT: Pattern recognition in neuroimaging distinguishes between two types of models: encoding- and decoding models. This distinction is based on the insight that brain state features, that are found to be relevant in an experimental paradigm, carry a different meaning in encoding- than in decoding models. In this paper, we argue that this distinction is not sufficient: Relevant features in encoding- and decoding models carry a different meaning depending on whether they represent causal- or anti-causal relations. We provide a theoretical justification for this argument and conclude that causal inference is essential for interpretation in neuroimaging.
    No preview · Conference Paper · Jun 2014
  • Sebastian Weichwald · Timm Meyer · Bernhard Scholkopf · Tonio Ball · Moritz Grosse-Wentrup
    [Show abstract] [Hide abstract]
    ABSTRACT: While invasively recorded brain activity is known to provide detailed information on motor commands, it is an open question at what level of detail information about positions of body parts can be decoded from non-invasively acquired signals. In this work it is shown that index finger positions can be differentiated from non-invasive electroencephalographic (EEG) recordings in healthy human subjects. Using a leave-one-subject-out cross-validation procedure, a random forest distinguished different index finger positions on a numerical keyboard above chance-level accuracy. Among the different spectral features investigated, high β-power (20-30 Hz) over contralateral sensorimotor cortex carried most information about finger position. Thus, these findings indicate that finger position is in principle decodable from non-invasive features of brain activity that generalize across individuals.
    No preview · Conference Paper · May 2014
  • Source
    Timm Meyer · Jan Peters · Thorsten O Zander · Bernhard Schölkopf · Moritz Grosse-Wentrup
    [Show abstract] [Hide abstract]
    ABSTRACT: Research on the neurophysiological correlates of visuomotor integration and learning (VMIL) has largely focused on identifying learning-induced activity changes in cortical areas during motor execution. While such studies have generated valuable insights into the neural basis of VMIL, little is known about the processes that represent the current state of VMIL independently of motor execution. Here, we present empirical evidence that a subject's performance in a 3D reaching task can be predicted on a trial-to-trial basis from pre-trial electroencephalographic (EEG) data. This evidence provides novel insights into the brain states that support successful VMIL. Six healthy subjects, attached to a seven degrees-of-freedom (DoF) robot with their right arm, practiced 3D reaching movements in a virtual space, while an EEG recorded their brain's electromagnetic field. A random forest ensemble classifier was used to predict the next trial's performance, as measured by the time needed to reach the goal, from pre-trial data using a leave-one-subject-out cross-validation procedure. The learned models successfully generalized to novel subjects. An analysis of the brain regions, on which the models based their predictions, revealed areas matching prevalent motor learning models. In these brain areas, the ¿/µ frequency band (8¿14 Hz) was found to be most relevant for performance prediction. VMIL induces changes in cortical processes that extend beyond motor execution, indicating a more complex role of these processes than previously assumed. Our results further suggest that the capability of subjects to modulate their ¿/µ bandpower in brain regions associated with motor learning may be related to performance in VMIL. Accordingly, training subjects in ¿/µ-modulation, e.g., by means of a brain-computer interface (BCI), may have a beneficial impact on VMIL.
    Full-text · Article · Mar 2014 · Journal of NeuroEngineering and Rehabilitation
  • [Show abstract] [Hide abstract]
    ABSTRACT: We provide a simple method, based on volume conduction models, to quantify the neurophysiological plausibility of independent components (ICs) reconstructed from EEG/MEG data. We evaluate the method on EEG data recorded from 19 subjects and compare the results with two established procedures for judging the quality of ICs. We argue that our procedure provides a sound empirical basis for the inclusion or exclusion of ICs in the analysis of experimental data.
    No preview · Conference Paper · Jun 2013
  • Moritz Grosse-Wentrup · Bernhard Schölkopf
    [Show abstract] [Hide abstract]
    ABSTRACT: The ability to operate a brain-computer interface (BCI) varies not only across subjects but also across time within each individual subject. In this article, we review recent progress in understanding the origins of such variations for BCIs based on the sensorimotor-rhythm (SMR). We propose a classification of studies according to four categories, and argue that an investigation of the neuro-physiological correlates of within-subject variations is likely to have a large impact on the design of future BCIs. We place a special emphasis on our own work on the neuro-physiological causes of performance variations, and argue that attentional networks in the gamma-range (\({>}40\) Hz) are likely to play a critical role in this context. We conclude the review with a discussion of outstanding problems.
    No preview · Chapter · Jan 2013
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The application of brain-computer interfaces (BCI) shows promising results in stroke rehabilitation, but the underlying neural substrates and processes of successful BCI-based neurorehabilitation remain unclear. The goal of our present work was to identify the brain areas associated with successful visuomotor integration and motor learning (VMIL), and investigate their connection with successful sensorimotor-rhythm (SMR)-modulation commonly used in stroke rehabil-itation related BCI systems. Our hypothesis was that neural processes associated with VMIL are linked to characteristics of the SMR, and thus share a common neural basis. Preliminary results indicate that the areas used to predict the current state of VMIL overlap with, but are not confined to, those areas used for SMR-based BCI training in stroke rehabilitation. This supports our hypothesis that VMIL and successful SMR modulation used in stroke BCI training share a common neural basis.
    Full-text · Article · Jan 2013
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Despite intensive efforts, no significant benefit of rehabilitation robotics in post-stroke motor-recovery has yet been demonstrated in large-scale clinical trials. The present work is based on the premise that future advances in rehabilitation robotics require an enhanced understanding of the neural processes involved in motor learning after stroke. We present a system that combines a Barret WAM™seven degree-of-freedom robot arm with neurophysiological recordings for the purpose of studying post-stroke motor learning. We used this system to conduct a pilot study on motor learning during reaching movements with two stroke patients. Preliminary results indicate that pre-trial brain activity in ipsilesional sensorimotor areas may be a neural correlate of the current state of motor learning. These results are discussed in terms of their relevance for future rehabilitation strategies that combine rehabilitation robotics with real-time analyses of neuro-physiological recordings.
    Full-text · Conference Paper · Oct 2012
  • Moritz Grosse-Wentrup · Bernhard Schölkopf
    [Show abstract] [Hide abstract]
    ABSTRACT: Subjects operating a brain-computer interface (BCI) based on sensorimotor rhythms exhibit large variations in performance over the course of an experimental session. Here, we show that high-frequency γ-oscillations, originating in fronto-parietal networks, predict such variations on a trial-to-trial basis. We interpret this finding as empirical support for an influence of attentional networks on BCI performance via modulation of the sensorimotor rhythm.
    No preview · Article · Jun 2012 · Journal of Neural Engineering
  • Source
    Dominik Janzing · David Balduzzi · Moritz Grosse-Wentrup · Bernhard Schoelkopf
    [Show abstract] [Hide abstract]
    ABSTRACT: Common methods of causal inference generate directed acyclic graphs (DAGs) that formalize causal relations between n variables. Given the joint distribution of all these variables, the DAG contains all information about how intervening on one variable would change the distribution of the other n-1 variables. It remains, however, a non-trivial question how to quantify the causal influence of one variable on another one. Here we propose a measure for causal strength that refers to direct effects and measure the "strength of an arrow" or a set of arrows. It is based on a hypothetical intervention that modifies the joint distribution by cutting the corresponding edge. The causal strength is then the relative entropy distance between the old and the new distribution. We discuss other measures of causal strength like the average causal effect, transfer entropy and information flow and describe their limitations. We argue that our measure is also more appropriate for time series than the known ones. Finally, we discuss conceptual problems in defining the strength of indirect effects.
    Full-text · Article · Mar 2012 · The Annals of Statistics
  • C. Davatzikos · M. Grosse-Wentrup · J. Mourao-Miranda · D. Van De Ville

    No preview · Article · Jan 2012
  • Source
    Dieter Devlaminck · Bart Wyns · Moritz Grosse-Wentrup · Georges Otte · Patrick Santens
    [Show abstract] [Hide abstract]
    ABSTRACT: Motor-imagery-based brain-computer interfaces (BCIs) commonly use the common spatial pattern filter (CSP) as preprocessing step before feature extraction and classification. The CSP method is a supervised algorithm and therefore needs subject-specific training data for calibration, which is very time consuming to collect. In order to reduce the amount of calibration data that is needed for a new subject, one can apply multitask (from now on called multisubject) machine learning techniques to the preprocessing phase. Here, the goal of multisubject learning is to learn a spatial filter for a new subject based on its own data and that of other subjects. This paper outlines the details of the multitask CSP algorithm and shows results on two data sets. In certain subjects a clear improvement can be seen, especially when the number of training trials is relatively low.
    Full-text · Article · Oct 2011 · Computational Intelligence and Neuroscience

Publication Stats

639 Citations
98.81 Total Impact Points

Institutions

  • 2012-2015
    • Max-Planck-Institut für Intelligente Systeme, Tübingen
      • • Max-Planck-Institute of Intelligent Systems
      • • Department of Empirical Inference
      Tübingen, Baden-Württemberg, Germany
  • 2011
    • University of Tuebingen
      • Centre for Integrative Neuroscience Werner Reichardt
      Tübingen, Baden-Württemberg, Germany
  • 2009-2011
    • Max Planck Institute for Biological Cybernetics
      • Department of Human Perception, Cognition and Action
      Tübingen, Baden-Württemberg, Germany
    • Universidad Autónoma de Madrid
      Madrid, Madrid, Spain
  • 2006-2009
    • Technische Universität München
      • Institute of Automatic Control Engineering (LSR)
      München, Bavaria, Germany