Publications of Machine Learning Group

Publications in Books


    2016

  • Farhad Arbabzadeh, Grégoire Montavon, Klaus-Robert Müller, and Wojciech Samek:
    Identifying individual facial expressions by deconstructing a neural network,
    Pattern Recognition - 38th German Conference, GCPR 2016, Lecture Notes in Computer Science, Springer-Verlag, vol. 9796, pp. 344-354, August 2016, doi:10.1007/978-3-319-45886-1_28, Book Chapter.
  • Alexander Binder, Grégoire Montavon, Sebastian Lapuschkin, Klaus-Robert Müller, and Wojciech Samek:
    Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers,
    Artificial Neural Networks and Machine Learning – ICANN 2016, Lecture Notes in Computer Science, Springer-Verlag, vol. 9887, pp. 63-71, August 2016, doi:10.1007/978-3-319-44781-0_8, Book Chapter.
  • Alexander Binder, Sebastian Bach, Grégoire Montavon, Klaus-Robert Müller, and Wojciech Samek:
    Layer-wise Relevance Propagation for Deep Neural Network Architectures,
    Information Science and Applications (ICISA) 2016, Lecture Notes in Electrical Engineering, Springer Singapore, vol. 376, pp. 913-922, February 2016, doi:10.1007/978-981-10-0557-2_87, Book Chapter.

  • 2015

  • Wojciech Samek:
    über die robuste räumliche Filterung von EEG in nichtstationären Umgebungen,
    in Steffen Hölldobler et al. (Editors), Ausgezeichnete Informatikdissertationen 2014, GI-Edition - Lecture Notes in Informatics (LNI), Bonner Köllen Verlag, pp. 251-260, 2015, Book Chapter.

Publications in Journals


    2017

  • Grégoire Montavon, Sebastian Lapuschkin, Alexander Binder, Wojciech Samek, and Klaus-Robert Müller:
    Explaining Nonlinear Classification Decisions with Deep Taylor Decomposition,
    Pattern Recognition, Elsevier Inc., vol. 65, pp. 211–222, May 2017, doi:10.1016/j.patcog.2016.11.008.
  • Ulrich Engelke, Daniel P. Darcy, Grant H. Mulliken, Sebastian Bosse, Maria G. Martini, Sebastian Arndt, Jan-Niklas Antons, Kit Yan Chan, Naeem Ramzan, and Kjell Brunnström:
    Psychophysiology-based QoE Assessment: A Survey,
    IEEE Journal of Selected Topics in Signal Processing. Special Issue on "Measuring QOE for advanced media technologies and services", February 2017, doi:10.1109/JSTSP.2016.2609843.

  • 2016

  • Irene Sturm, Sebastian Lapuschkin, Wojciech Samek, and Klaus-Robert Müller:
    Interpretable Deep Neural Networks for Single-Trial EEG Classification,
    Journal of Neuroscience Methods, Elsevier Inc., vol. 274, pp. 141-145, December 2016, doi:10.1016/j.jneumeth.2016.10.008.
  • Wojciech Samek, Duncan Blythe, Klaus-Robert Müller, Benjamin Blankertz, and Vadim V. Nikulin:
    Multiscale temporal neural dynamics predict performance in a complex sensorimotor task,
    NeuroImage, Elsevier Inc., vol. 141, pp. 291–303, November 2016, doi:10.1016/j.neuroimage.2016.06.056.
  • Wojciech Samek, Alexander Binder, Grégoire Montavon, Sebastian Lapuschkin, and Klaus-Robert Müller:
    Evaluating the visualization of what a Deep Neural Network has learned,
    IEEE Transactions on Neural Networks and Learning Systems, 2016, doi:10.1109/TNNLS.2016.2599820.
  • Stephanie Brandl, Laura Frølich, Johannes Höhne, Klaus-Robert Müller, and Wojciech Samek:
    Brain-Computer Interfacing under Distraction: An Evaluation Study,
    Journal of Neural Engineering, IOP Publishing, vol. 13, no. 5, pp. 056012, August 2016, doi:10.1088/1741-2560/13/5/056012.
  • G. Weber, O. Böpple, M. Weber, Paul Chojecki, Detlef Ruschin, K. Köppe, S. Glende, et al.:
    DIN SPEC 91333:2016-08 (D): Berührungslose Gestensteuerung zur Mensch-System-Interaktion (Contactless gesture control for human-system interaction),
    Technische Regel DIN Spec No. 91333:2016-08 (D), Beuth Verlag, Berlin, Germany, August 2016, further information.
  • Paul Chojecki, Detlef Ruschin, and David Przewozny:
    Let 's talk about Gestures! Ein Notationssystem zur Beschreibung räumlicher Gesten in der Entwicklung interaktiver Mensch-Technik-Systeme,
    Bullinger, A.C. (Hrsg.), 3D SENSATION - transdisziplinäre Perspektiven. Verlag aw&I Wissenschaft und Praxis, Chemnitz, Germany, ISBN 978-3-944192-07-9, June 2016, download.
  • Wojciech Samek:
    On robust spatial filtering of EEG in nonstationary environments,
    it-Information Technology, Distinguished Dissertations, vol. 58, no. 3, pp. 150–154, June 2016, doi:10.1515/itit-2016-0023.
  • Sebastian Lapuschkin, Alexander Binder, Grégoire Montavon, Klaus-Robert Müller, and Wojciech Samek:
    The Layer-wise Relevance Propagation Toolbox for Artificial Neural Networks,
    Journal of Machine Learning Research, vol. 17, no. 114, pp. 1-5, 2016.

  • 2015

  • Sven Dähne, Felix Bießmann, Wojciech Samek, Stefan Haufe, Dominique Goltz, Christopher Gundlach, Arno Villringer, Siamac Fazli, and Klaus-Robert Müller:
    Multivariate Machine Learning Methods for Fusing Multimodal Functional Neuroimaging Data,
    Proceedings of the IEEE, vol. 103, no. 9, pp. 1507-1530, September 2015, doi:10.1109/JPROC.2015.2425807, Invited Paper.
  • Sebastian Bach, Alexander Binder, Grégoire Montavon, Frederick Klauschen, Klaus-Robert Müller, and Wojciech Samek:
    On Pixel-wise Explanations for Non-Linear Classifier Decisions by Layer-wise Relevance Propagation,
    PLOS ONE, vol. 10, no. 7, pp. e0130140, July 2015, doi:10.1371/journal.pone.0130140.
  • Siamac Fazli, Sven Dähne, Wojciech Samek, Felix Bießmann, and Klaus-Robert Müller:
    Learning from more than one Data Source: Data Fusion Techniques for Sensorimotor Rhythm-based Brain-Computer Interfaces,
    Proceedings of the IEEE, vol. 103, no. 6, pp. 891-906, June 2015, doi:10.1109/JPROC.2015.2413993, Invited Paper.
  • Forooz Shahbazi, Arne Ewald, and Guido Nolte:
    Self-Consistent MUSIC: An approach to the localization of true brain interactions from EEG/MEG data,
    NeuroImage, vol. 112, pp. 299-309, May 2015, doi:10.1016/j.neuroimage.2015.02.054.
  • Laura Acqualagna, Sebastian Bosse, Anne K. Porbadnigk, Gabriel Curio, Klaus-Robert Müller, Thomas Wiegand, and Benjamin Blankertz:
    EEG-based classification of video quality perception using steady state visual evoked potentials (SSVEPs),
    Journal of Neural Engineering, vol. 12, no. 2, pp. 026012, March 2015, doi:10.1088/1741-2560/12/2/026012.

Publications in Conference Proceedings


    2017

  • Vignesh Srinivasan, Sebastian Lapuschkin, Cornelius Hellge, Klaus-Robert Müller, and Wojciech Samek:
    Interpretable human action recognition in compressed domain,
    Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017), New Orleans, LA, USA, March 2017.

  • 2016

  • Wojciech Samek, Grégoire Montavon, Alexander Binder, Sebastian Lapuschkin, and Klaus-Robert Müller:
    Interpreting the Predictions of Complex ML Models by Layer-wise Relevance Propagation,
    Proceedings of the Interpretable ML for Complex Systems Workshop at the Conference on Neural Information Processing Systems (NIPS), Barcelona, Spain, December 2016.
  • Sebastian Bosse, Dominique Maniry, Klaus-Robert Müller, Thomas Wiegand, and Wojciech Samek:
    Neural Network-Based Full-Reference Image Quality Assessment,
    Proceedings of the Picture Coding Symposium (PCS), Nürnberg, Germany, December 2016.
  • Vignesh Srinivasan, Serhan Gül, Sebastian Bosse, Jan Timo Meyer, Thomas Schierl, Cornelius Hellge and Wojciech Samek:
    On the robustness of action recognition methods in compressed and pixel domain,
    Proceedings of the European Workshop on Visual Information Processing (EUVIP), Marseille, France, pp. 1-6, October 2016, doi:10.1109/EUVIP.2016.7764584.
  • Sebastian Bosse, Klaus-Robert Müller, Thomas Wiegand, and Wojciech Samek:
    Brain-Computer Interfacing for Multimedia Quality Assessment,
    Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC), Budapest, Hungary, pp. 002834-002839, October 2016, doi:10.1109/SMC.2016.7844669.
  • Stephanie Brandl, Klaus-Robert Müller, and Wojciech Samek:
    Alternative CSP approaches for multimodal distributed BCI data,
    Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC), Budapest, Hungary, pp. 003742-003747, October 2016, doi:10.1109/SMC.2016.7844816.
  • Serhan Gül, Jan Timo Meyer, Thomas Schierl, Cornelius Hellge, and Wojciech Samek:
    Hybrid Video Object Tracking in H.265/HEVC Video Streams,
    Proceedings of the International Workshop on Multimedia Signal Processing (MMSP), Montreal, Canada, pp. 1-5, September 2016, doi:10.1109/MMSP.2016.7813363.
  • Sebastian Bach, Alexander Binder, Klaus-Robert Müller, and Wojciech Samek:
    Controlling Explanatory Heatmap Resolution and Semantics via Decomposition Depth,
    Proceedings of the IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA, pp. 2271-2275, September 2016, doi:10.1109/ICIP.2016.7532763.
  • Sebastian Bosse, Dominique Maniry, Thomas Wiegand, and Wojciech Samek:
    A Deep Neural Network for Image Quality Assessment,
    Proceedings of the IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA, pp. 3773-3777, September 2016, doi:10.1109/ICIP.2016.7533065.
  • Sebastian Bosse, Qiaobo Chen, Mischa Siekmann, Wojciech Samek, and Thomas Wiegand:
    Shearlet-based Reduced Reference Image Quality Assessment,
    Proceedings of the IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA, pp. 2052-2056, September 2016, doi:10.1109/ICIP.2016.7532719.
  • Leila Arras, Franziska Horn, Grégoire Montavon, Klaus-Robert Müller, and Wojciech Samek:
    Explaining Predictions of Non-Linear Classifiers in NLP,
    Proceedings of the Workshop on Representation Learning for NLP at Association for Computational Linguistics Conference (ACL), Berlin, Germany, pp. 1-7, August 2016.
  • Sebastian Bosse, Mischa Siekmann, Jennifer Rasch, Thomas Wiegand, and Wojciech Samek:
    Quality Assessment of Image Patches Distorted by Image Compression Using Crowdsourcing,
    Proceedings of the IEEE International Conference on Multimedia and Expo (ICME), Seattle, WA, USA, pp. 1-6, July 2016, doi:10.1109/ICME.2016.7552958.
  • Sebastian Lapuschkin, Alexander Binder, Grégoire Montavon, Klaus-Robert Müller, and Wojciech Samek:
    Analyzing Classifiers: Fisher Vectors and Deep Neural Networks,
    Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 2912-2920, June 2016, doi:10.1109/CVPR.2016.318.
  • Grégoire Montavon, Sebastian Bach, Alexander Binder, Wojciech Samek, and Klaus-Robert Müller:
    Deep Taylor Decomposition of Neural Networks,
    Proceedings of the Workshop on Visualization for Deep Learning at 33rd International Conference on Machine Learning (ICML), New York City, USA, June 2016.
  • Alexander Binder, Wojciech Samek, Grégoire Montavon, Sebastian Bach, and Klaus-Robert Müller:
    Analyzing and Validating Neural Networks Predictions,
    Proceedings of the Workshop on Visualization for Deep Learning at 33rd International Conference on Machine Learning (ICML), New York City, USA, June 2016, Best Paper Prize.
  • Sebastian Bosse, Dominique Maniry, Klaus-Robert Müller, Thomas Wiegand and Wojciech Samek:
    Full-Reference Image Quality Assessment Using Neural Networks,
    Proceedings of the 8th International Conference on Quality of Multimedia Experience (QoMEX), Lisbon, Portugal, June 2016, Short Paper.

  • 2015

  • Carmen Vidaurre, Claudia Sannelli, Wojciech Samek, Sven Dähne, and Klaus-Robert Müller:
    Machine Learning Methods of the Berlin Brain-Computer Interface,
    Proceedings of the 9th IFAC Symposium on Biological and Medical Systems, Berlin, Germany, pp. 447-452, September 2015, doi:10.1016/j.ifacol.2015.10.181.
  • Andre Seixas Dias, Mischa Siekmann, Sebastian Bosse, Heiko Schwarz, Detlev Marpe and Marta Mrak:
    Rate-distortion optimised quantisation for HEVC using spatial just noticeable distortion,
    Proceedings of the European Signal Processing Conference (EUSIPCO), Nice, France, pp. 110-114, August 2015, doi:10.1109/EUSIPCO.2015.7362355.
  • Laura Frølich, Irene Winkler, Klaus-Robert Müller, and Wojciech Samek:
    Investigating effects of different artefact types on Motor Imagery BCI,
    Proceedings of 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Milano, Italy, pp. 1942-1945, August 2015, doi:10.1109/EMBC.2015.7318764.
  • Wojciech Samek and Klaus-Robert Müller:
    Tackling noise, artifacts and nonstationarity in BCI with robust divergences,
    Proceedings of the European Signal Processing Conference (EUSIPCO), Nice, France, pp. 2791-2795, August 2015, doi:10.1109/EUSIPCO.2015.7362883.
  • Detlef Ruschin:
    Maintaining patients' social contacts through displaying nonverbal awareness information on mobile devices,
    Proceedings of 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Milano, Italy, pp. 7744-7747, August 2015, doi:10.1109/EMBC.2015.7320187.
  • Sebastian Bosse, Anne K. Porbadnigk, Gabrial Curio, Klaus-Robert Müller, Benjamin Blankertz and Thomas Wiegand:
    Neurophysiological assessment of perceived image quality using steady-state visual evoked potentials,
    Proceedings of SPIE 9599, Applications of Digital Image Processing XXXVIII, San Diego, USA, pp. 1987-1991, August 2015, doi:10.1117/12.2193684.
  • Andre Seixas Dias, Sebastian Schwarz, Sebastian Bosse, Mischa Siekmann, Heiko Schwarz, Detlev Marpe, John Zubrzycki, and Marta Mrak:
    Perceptually optimized video compression,
    IEEE International Conference on Multimedia and Expo Workshops (ICMEW) 2015, Torino, Italy, pp. 1-4, July 2015, doi:10.1109/ICMEW.2015.7169819.
  • Stephanie Brandl, Johannes Höhne, Klaus-Robert Müller, and Wojciech Samek:
    Bringing BCI into everyday life: Motor imagery in a pseudo realistic environment,
    Proceedings of the International IEEE/EMBS Neural Engineering Conference (NER), Montpellier, France, pp. 224-227, April 2015, doi:10.1109/NER.2015.7146600.
  • Stephanie Brandl, Klaus-Robert Müller, and Wojciech Samek:
    Robust Common Spatial Patterns based on Bhattacharyya Distance and Gamma Divergence,
    Proceedings of the IEEE International Winter Workshop on Brain-Computer Interface (BCI), Jeongsun-Kun, Korea, pp. 1-4, January 2015, doi:10.1109/IWW-BCI.2015.7073030.

Talks and Tutorials


    2017

  • Wojciech Samek:
    Interpretable Machine Learning,
    39th German Conference on Pattern Recognition (GCPR), Basel, Switzerland, September 2017, Tutorial.
  • Wojciech Samek:
    Methods for Interpreting and Understanding Deep Neural Networks,
    IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, LA, USA, March 2017, Tutorial.

  • 2016

  • Wojciech Samek:
    Interpretable Deep Learning,
    Quo Vadis Game Developer Conference, Berlin, Germany, April 2016.
  • Wojciech Samek:
    Effective Data Analytics,
    Big Data Excellence for Utilities Conference, Berlin, Germany, February 2016.

  • 2015

  • Wojciech Samek:
    Explaining individual deep network predictions and measuring the quality of these explanations,
    Feature Extraction Workshop: Modern Questions and Challenges, NIPS workshop, Montreal, Canada, December 2015.
  • Wojciech Samek:
    Divergence-based Spatial Filtering for robust BCI,
    Germany-Japan Adaptive BCI Workshop, Kyoto, Japan, October 2015.
  • Wojciech Samek:
    The Machine Learning way to Video Analysis and Compression,
    Trends in Video Analysis, Representation and Delivery Workshop, Aachen, Germany, February 2015.