Prof. Dr. Heiko Wersing

My main research interests include incremental & online learning, personalization, adaptive HMI, biologically motivated computer vision, sparse coding.  

Publications

Recent updates

Journals

Human Machine Interaction & Cooperation, Personalization

• N. Schoemig, M. Heckmann, H.Wersing, C. Maag, and A. Neukum. Please watch right: Evaluation of a speech-based on-demand assistance system for urban intersections. Transportation Research F 54:196-210 (2018) (PDF)
  
  
• M. Heckmann, H.Wersing, D. Orth and D. Kolossa. 'Assistance-on-demand': Development of a speech-based, personalized left-turning assistant. Automobiltechnische Zeitung ATZ (5), pp.38-43 (2017). (PDF)
  
  
• A. Ceravola, F. Joublin, H. Wersing, S. Hasler, B. Dariush, Y. Chen. A Data Management Infrastructure for Intelligent Systems. Journal of the Japanese Society for Artificial Intelligence 33(1):45-54 (2018). (PDF)
  
  
• C. Lang, S. Wachsmuth, M. Hanheide, and H. Wersing. Facial Communicative Signals - Valence Recognition in Task-Oriented Human-Robot Interaction. International Journal of Social Robotics 4(3):249-262 (2012). (PDF)
  
  

Online & incremental learning

• V. Losing, B. Hammer and H. Wersing. Tackling Heterogeneous Concept Drift with the Self-Adjusting Memory (SAM). Knowledge and Information Systems 54(1):171-201 (2018). (PDF)
  
  
• V. Losing, B. Hammer, and H. Wersing. Incremental On-line Learning: A Review and Comparison of State of the Art Algorithms. Neurocomputing (2017). (PDF)
  
  
• L. Fischer, B. Hammer and H. Wersing. Optimal Local Rejection for Classifiers. Neurocomputing 214:445-457. (2016). (PDF)
  
  
• L. Fischer, B. Hammer and H. Wersing. Efficient Rejection Strategies for Prototype-based Classification. Neurocomputing 169:334-342. (2015). (PDF)
  
  
• S. Kirstein, H. Wersing, H.-M. Gross, and E. Körner. A Life-Long Learning Vector Quantization Approach for Interactive Learning of Multiple Categories. Neural Networks 28:90-205 (2012). (PDF)
  
  
• S. Kirstein, A. Denecke, S. Hasler, H. Wersing, H.-M. Gross, and E. Körner. A Vision Architecture for Unconstrained and Incremental Learning of Multiple Categories. Memetic Computing 1(4):291-304. (2009). (PDF)
  
  
• S. Kirstein, H. Wersing, and E. Körner. A Biologically Motivated Visual Memory Architecture for Online Learning of Objects. Neural Networks 21:65-77 (2008). (PDF)
  
  
• H. Wersing, S.Kirstein, M. Goetting, H. Brandl, M. Dunn, I. Mikhailova, C. Goerick, J.J. Steil, H. Ritter, and E. Körner. Online Learning of Objects in a Biologically Motivated Architecture. International Journal of Neural Systems 17:219-230 (2007). (PDF)
  
  

Biologically motivated computer vision, robotics, & sparse coding

• A. Andreopoulos, S. Hasler, H. Wersing, H. Janssen, J. Tsotsos, and E. Körner. Active 3D Object Localization Using a Humanoid Robot. IEEE Transactions on Robotics 27(1):47-64 (2011). (PDF)
  
  
• K. Hosoda, M. Watanabe, H. Wersing, E. Körner, H. Tsujino, H. Tamura, I. Fujita. A model for learning topographically organized parts-based representations of objects in visual cortex: topographic non-negative matrix factorization. Neural Computation 21(9):2605-2633 (2009). (PDF)
  
  
• A. Denecke, H. Wersing, J.J. Steil, and E. Körner. Online Figure-Ground Segmentation with Adaptive Metrics in Generalized LVQ. Neurocomputing 72(7-9):1470-1482 (2009). (PDF)
  
  
• S. Hasler, H. Wersing, and E. Körner. Combining reconstruction and discrimination with class-specific sparse coding. Neural Computation 19:1897-1918 (2007). (PDF)
  
  
• J.J. Steil, M. Goetting, H. Wersing, E. Körner, and H. Ritter. Adaptive scene-dependent filters for segmentation and online learning of visual objects. Neurocomputing 70:1235-1246 (2007). (PDF)
  
  
• G. Schneider, H. Wersing, B. Sendhoff, and E. Körner. Evolutionary optimization of a hierarchical object recognition model. IEEE Trans. Systems, Man, Cybernetics, Part B: Cybernetics. 35(3):426- 437 (2005). (PDF)
  
  
• Heiko Wersing and Edgar Körner. Learning optimized features for hierarchical models of invariant recognition. Neural Computation 15(7):1559-1588 (2003). (PDF)

Feature binding, segmentation and perceptual grouping

• S. Weng, H. Wersing, J.J. Steil, and H. Ritter. Learning lateral interactions for feature binding and sensory segmentation from prototypic basis interactions. IEEE Trans. Neural Networks 17(4):843--862. (2006). (PDF)
  
  
• Jörg Ontrup, Heiko Wersing, and Helge Ritter. A computational feature binding model of human texture perception. Cognitive Processing 5: 31-44 (2004). (PDF).
  
  
• T. W. Nattkemper, H. Wersing, W. Schubert, and H. Ritter. A Neural Network Architecture for Automatic Segmentation of Fluorescence Micrographs. Neurocomputing 48(4):357-367 (2002). (PDF).
  
  
• Heiko Wersing, Jochen J. Steil, and Helge Ritter. A competitive layer model for feature binding and sensory segmentation. Neural Computation 13(2):357-387 (2001). (PDF).

Neurodynamics

• Heiko Wersing, Wolf-Jürgen Beyn, and Helge Ritter. Dynamical stability conditions for recurrent neural networks with unsaturating piecewise linear transfer functions. Neural Computation 13(8):1811-1825 (2001). (PDF).

Books and Book Chapters

• S. Kirstein and H. Wersing. Incremental Learning of Visual Categories. Encyclopedia of the Sciences of Learning. Edited by Norbert Seel. Springer(2011). (PDF)
  
  
• J. Eggert and H. Wersing. Approaches and Challenges for Cognitive Vision Systems. Creating Brain-like Intelligence Symposium. Edited by B. Sendhoff, E. Koerner, O. Sporns, H. Ritter and K. Doya. Published by Springer (2009). (PDF).


• Heiko Wersing. Spatial Feature Binding and Learning in Competitive Neural Layer Architectures PhD Thesis. Faculty of Technology, University of Bielefeld, March 2000. Published by Cuvillier, Goettingen (144 pages, 1.8 MB gzipped Postscript).

Conference Papers

Human Machine Interaction & Cooperation, Personalization

• M. Krueger, C. Wiebel-Herboth, and H. Wersing. Approach for Enhancing the Perception and Prediction of Traffic Dynamics with a Tactile Interface. Proc. Automotive User Interfaces AutoUI (2018). (PDF)
  
  
• M. Krueger, C. Wiebel, and H. Wersing. From tools towards cooperative assistants. Proc. Int. Conf. on Human Agent Interaction HAI (2017). (PDF)
  
  
• M. Heckmann, H.Wersing, D. Orth, D. Kolossa, Nadja Schoemig, Christian Maag, and Mark Dunn. Towards an on-demand intersection assistant -initial user acceptance and system development-. Proc. FAST-zero Conference (2017). (PDF)
  
  
• M. Hasenjaeger and H. Wersing. Personalization in Advanced Driver Assistance Systems and Autonomous Vehicles: A Review. IEEE Int. Conf. on Intelligent Transportation Systems. ITSC (2017). (PDF)
  
  
• V. Losing, B. Hammer, and H. Wersing. Personalized Maneuver Prediction at Intersections. IEEE Int. Conf. on Intelligent Transportation Systems. ITSC (2017). (PDF)
  
  
• N. Schoemig, M. Heckmann, C. Maag, A. Neukum and H. Wersing. "Assistance-On-Demand": a Speech-based Assistance System for Urban Intersections. Proc. Automotive User Interfaces. (2016). (PDF)
  
  
• C. Lang, S. Wachsmuth, M. Hanheide, and H. Wersing. Facial Communicative Signal Interpretation in Human-Robot Interaction by Discriminative Subsequence Selection. IEEE Int. Conf on Robotics and Automation ICRA (2013). Karlsruhe. (PDF)
  
  
• C. Lang, S. Wachsmuth, H. Wersing, and M. Hanheide. Facial Expressions as Feedback Cue in Human-Robot Interaction - A Comparison between Human and Automatic Recognition Performances. CVPR Workshop for Human Communicative Behavior Analysis. (2010). San Francisco. (PDF)
  
  
• C. Lang, M. Hanheide, M. Lohse, H. Wersing, and G. Sagerer. Feedback intepretation based on facial expressions in human-robot interaction. Proc. IEEE Ro-Man (2009) Toyama, Japan. (PDF)
  
  

Online & incremental learning

• V. Losing, B. Hammer and H. Wersing. Enhancing Very Fast Decision Trees Using Local Split-Time Prediction. IEEE Int. Conf. on Data Mining. ICDM (2018). (PDF)
  
  
• C. Limberg, H.Wersing, and H. Ritter. Efficient Accuracy Estimation for Instance-based Incremental Active Learning. Europ. Symp. Artif. Neural Networks. ESANN (2018). (PDF)
  
  
• C. Limberg, H.Wersing, and H. Ritter. Improving Active Learning by Avoiding Ambiguous Samples. Int. Conf. Artif. Neural Networks. ICANN (2018). (PDF)
  
  
• J. P. Goepfert, B. Hammer, and H. Wersing. Mitigating the Adverse Effects of Concept Drift via the Application of Reject Option. Int. Conf. Artif. Neural Networks. ICANN (2018). (PDF)
  
  
• V. Losing, B. Hammer, and H. Wersing. Self-Adjusting Memory: How to Deal with Diverse Drift Types. Int. Joint Conf. on Artif. Intell. IJCAI (2017). (PDF)
  
  
• V. Losing, B. Hammer and H. Wersing. KNN Classifier with Self-Adjusting Memory for Heterogeneous Concept Drift. IEEE Int. Conf. on Data Mining. ICDM (2016). Best paper award. (PDF)
  
  
• L. Fischer, S. Hasler, S. Schrom and H. Wersing. Improving Online Learning of Visual Categories by Deep Features. NIPS Workshop on the Future of Interactive Learning Machines. (2016). (PDF)
  
  
• V. Losing, B. Hammer and H. Wersing. Dedicated Memory Models for Continual Learning in the Presence of Drift. NIPS Workshop on Continual Learning and Deep Networks. (2016). (PDF)
  
  
• V. Losing, B. Hammer and H. Wersing. Choosing the Best Algorithm for an Incremental On-line Learning Task. Proc. Europ. Symp. on Artif. Neur. Netw. ESANN. (2016). (PDF)
  
  
• L. Fischer, B. Hammer and H. Wersing. Online Metric Learning for an Application to Concept Drift. Proc. Int. Joint Conf. Artif. Neur. Netw. IJCNN. (2016). (PDF)
  
  
• V. Losing, B. Hammer and H. Wersing. Interactive Online Learning for Obstacle Classification on a Mobile Robot. Proc. Int. Joint Conf. Artif. Neur. Netw. IJCNN. (2015). (PDF)
  
  
• L. Fischer, B. Hammer and H. Wersing. Combining Offline and Online Classifiers for Life-long Learning. Proc. Int. Joint Conf. Artif. Neur. Netw. IJCNN. pp.2808-2815 (2015). (PDF)
  
  
• L. Fischer, B. Hammer and H. Wersing. Certainty-based Prototype Insertion/Deletion for Prototype-based Classification with Metric Adaptation. Proc. Eur. Symp. Art. Neur. Netw. ESANN. pp 7-12 (2015). (PDF)
  
  
• L. Fischer, B. Hammer and H. Wersing. Local Rejection Strategies for Learning Vector Quantization . Proc. Int. Conf. Artif. Neur. Netw. ICANN. pp.563-570 (2014). (PDF)
  
  
• L. Fischer, B. Hammer and H. Wersing. Rejection Strategies for Learning Vector Quantization. Proc. Eur. Symp. Art. Neur. Netw. ESANN. pp 41-46 (2014). (PDF)
  
  
• L. Fischer, D. Nebel, T. Villmann, B. Hammer and H. Wersing. Rejection Strategies for Learning Vector Quantization - A Comparison of Probabilistic and Deterministic Approaches. Proc. Workshop on Self-organizing Maps WSOM. pp.109-118. Best student paper award. (2014). (PDF)
  
  
• S. Kirstein and H. Wersing. A Biologically Inspired Approach for Interactive Learning of Categories. Proc. Int. Conf. on Development and Learning. ICDL (2011), Frankfurt. (PDF)
  
  
• S. Kirstein, H. Wersing, and E. Körner. Towards autonomous bootstrapping for life-long learning categorization tasks. Proc. Int. Joint Conf. on Neur. Networks. IJCNN (2010), Barcelona. pp. 4075-82. (PDF)
  
  
• S. Kirstein, H. Wersing, H-M. Gross, and E. Körner. A Vector Quantization Approach for Life-Long Learning of Categories. Proc. Int. Conf. on Neur. Inform. Proc. ICONIP 2008, Auckland. pp.805-812. Best paper award. (PDF)
  
  
• S. Kirstein, H. Wersing, H-M. Gross, and E. Körner. An Integrated System for Incremental Learning of Multiple Visual Categories. Proc. Int. Conf. on Neur. Inform. Proc. ICONIP 2008, Auckland. pp.813-820. (PDF)
  
  
• H. Wersing, S.Kirstein, M. Goetting, H. Brandl, M. Dunn, I. Mikhailova, C. Goerick, J.J. Steil, H. Ritter, and E. Körner. Online learning of objects and faces in an integrated biologically motivated architecture. Proc. Int. Conf. on Computer Vision Systems ICVS 2007, Bielefeld. (PDF)
  
  
• H. Wersing, S.Kirstein, M. Goetting, H. Brandl, M. Dunn, I. Mikhailova, C. Goerick, J.J. Steil, H. Ritter, and E. Körner. A biologically motivated system for unconstrained online learning of visual objects. Proc. Int. Conf. Artif. Neural Networks ICANN 2006, Athens. Vol. 2, pp. 508-517. (PDF)
  
  
• J.J. Steil, H. Wersing. Recent trends in online learning for cognitive robotics. Proc. Eur. Symposium Artif. Neural Networks ESANN 2006, Bruges. pp 77-78. (PDF)
  
  
• S. Kirstein, H. Wersing, and E. Körner. Rapid online learning of objects in a biologically motivated recognition architecture. Proc. 27th Pattern Recognition Symposium DAGM 2005, Vienna. pp. 301-308. (PDF)
  
  
• S. Kirstein, H. Wersing, and E. Körner. Online learning for object recognition with a hierarchical visual cortex model. Proc. Int. Conf. on Artif. Neur. Netw. ICANN 2005, Warsaw. pp. 487-492. (PDF)

Biologically motivated computer vision & robotics

• J. Schmuedderich, N. Einecke, S. Hasler, A. Gepperth, B. Bolder, R. Kastner, M. Franzius, S. Rebhan, B. Dittes, H. Wersing, J. Eggert, J. Fritsch, C. Goerick System approach for multi-purpose representations of traffic scene elements. Proc IEEE Intelligent Transportation Systems. Madeira. (2010). (PDF)
  
  
• A. Denecke, I. Ayllon-Clemente, H. Wersing, J. Eggert, and J.J. Steil. Figure-ground Segmentation using Metrics Adaptation in Level Set Methods. Proc. European Symposium on Artificial Neural Networks ESANN (2010) Bruges, Belgium. (PDF)
  
  
• S. Hasler, H. Wersing, and E. Körner. Large-scale Real-time Object Identification Based on Analytic Features. Proc. Int. Conf. on Artif. Neur. Netw. ICANN 2009, Limassol, Cyprus. pp.663-672. (PDF)
  
  
• A. Denecke, H. Wersing, J.J. Steil, and E. Körner. Incremental Figure-Ground Segmentation Using Localized Adaptive Metrics in LVQ. Proc. 7th International Workshop on Self-Organizing Maps (WSOM 2009) St. Augustine, Florida, USA. (PDF)
  
  
• A. Denecke, H. Wersing, J.J. Steil, and E. Körner. Robust object segmentation by adaptive metrics in Generalized LVQ. Proc. Eur. Symposium Artif. Neural Networks ESANN 2008, Bruges. pp.319-324 (PDF)
  
  
• H. Wersing, S.Kirstein, B. Schneiders, U. Bauer-Wersing, and E. Körner. Online Learning for Bootstrapping of Object Recognition and Localization in a Biologically Motivated Architecture. Proc. Int. Conf. on Computer Vision Systems ICVS 2008, Santorini. (PDF)
  
  
• C. Goerick, B. Bolder, H. Janssen, M. Gienger, H. Sugiura, M. Dunn, I. Mikhailova, T. Rodemann, H. Wersing and S. Kirstein. Towards Incremental Hierarchical Behavior Generation for Humanoids. Proc. IEEE/RSJ Int. Conf. on Humanoid Robots (Humanoids 2007), Genova, Italy. (PDF)
  
  
• C. Goerick, I. Mikhailova, H. Wersing, and S. Kirstein. Biologically motivated visual behaviours for humanoids: Learning to interact and learning in interaction. Proc. IEEE/RSJ Int. Conf. on Humanoid Robots (Humanoids 2006), Genova, Italy. (PDF)
  
  
• M. Goetting, J.J. Steil, H. Wersing, E. Körner, and H. Ritter. Adaptive scene-dependent filters in online learning environments. Proc. Eur. Symposium Artif. Neural Networks ESANN 2006, Bruges. pp 101-106. (PDF)
  
  
• C. Goerick, H. Wersing, I. Mikhailova, and M. Dunn. Peripersonal space and object recognition for humanoids. Proc. IEEE/RSJ Int. Conf. on Humanoid Robots (Humanoids 2005), Tsukuba, Japan. (PDF)
  
  

Sparse coding, feature learning and generative models

• D. Dornbusch, R. Haschke, S. Menzel, and H. Wersing. Decomposition of Multimodal Data for Affordance-based Identification of Potential Grasps. Int. Conf. on Pattern Recognition Applications and Methods(ICPRAM), Vilamoura, Algarve (2012). accepted. (PDF).
  
  
• M. Franzius and H. Wersing. Learning Invariant Visual Shape Representations from Physics. Proc. Int. Conf. on Art. Neur. Networks. ICANN (2010), Thessaloniki. pp. 298-302. (PDF)
  
  
• S. John, H. Wersing, and H. Ritter. An iterative approach to local-PCA. Proc. Int. Joint Conf. on Neur. Networks. IJCNN (2010), Barcelona. (PDF)
  
  
• D. Dornbusch, R. Haschke, S. Menzel, and H. Wersing. Finding Correlations in Multimodal Data Using Decomposition Approaches. Proc. European Symposium on Artificial Neural Networks (ESANN), (2010). accepted. (PDF).
  
  
• D. Dornbusch, R. Haschke, S. Menzel, and H. Wersing. Correlating Shape and Functional Properties Using Decomposition Approaches. In 23rd Florida Artificial Intelligence Research Society Conference (FLAIRS-23), (2010). accepted. (PDF).
  
  
• Z. Bozakov, L. Graening, S. Hasler, H. Wersing, and S. Menzel. Unsupervised Extraction of Design Components for a 3D parts-based Representation. In IEEE IJCNN 2008, Hong Kong. accepted. (PDF).
  
  
• S. Hasler, H. Wersing, and E. Körner. A Comparison of Features in Parts-based Object Recognition Hierarchies. Proc. Int. Conf. on Artif. Neur. Netw. ICANN 2007, Porto. pp 210-219. (PDF)
  
  
• S. Hasler, H. Wersing, and E. Körner. Class-specific sparse coding for learning of object representations. Proc. Int. Conf. on Artif. Neur. Netw. ICANN 2005, Warsaw. pp 475-480. (PDF)
  
  
• J. Eggert, H. Wersing, and E. Körner. Transformation-invariant representation and NMF. Proc. Int. Joint Conf. on Neur. Netw. IJCNN 2004, Budapest, pages 2535-2539 (PDF)
  
  
• H. Wersing , J. Eggert, and E. Körner. Sparse Coding with Invariance Constraints. Proc. Int. Conf. on Art. Neur. Netw. ICANN 2003, Istanbul, pages 385-392 (PDF)
  
  
• Heiko Wersing and Edgar Körner. Unsupervised Learning of Combination Features for Hierarchical Recognition Models. Proc. Int. Conf. on Art. Neur. Netw. ICANN 2002, Madrid, pages 1225-1230 (PDF)

Hierarchical feature learning in auditory processing

• X. Domont, M. Heckmann, H. Wersing, F. Joublin, and C. Goerick. A hierarchical model for syllable recognition. Proc. European Symposium on Artificial Neural Networks ESANN 2007. (PDF).
  
  
• X. Domont, M. Heckmann, H. Wersing, F. Joublin, S. Menzel, B. Sendhoff, and C. Goerick. Word recognition with a hierarchical network. Nonlinear Speech Processing Workshop NOLISP 2007, Barcelona. (PDF).
  
  

Evolutionary optimization

• V.R. Khare, X. Yao, B. Sendhoff, Y. Jin, and H. Wersing. Co-evolutionary Modular Neural Networks for Automatic Problem Decomposition. In 2005 Congress on Evolutionary Computation, Edinburgh. IEEE. pp. 2691-2698. (PDF).
  
  
• Alexandra Mark, Bernhard Sendhoff, and Heiko Wersing. A decision making framework for game playing using evolutionary optimization and learning. In 2004 Congress on Evolutionary Computation, volume 1, pages 373-380, Portland, OR, June 2004. IEEE. (PDF).
  
  
• Alexandra Mark, Bernhard Sendhoff, and Heiko Wersing. Evolution of a learning and anticipating decision system. In Horst-Michael Gross, Klaus Debes, and Hans-Joachim Boehme, editors, Third Workshop on SelfOrganization of AdaptiVE Behavior (SOAVE 2004) Ilmenau, pages 271-281, VDI-Verlag Duesseldorf 2004. (PDF).
  
  
• G. Schneider, H. Wersing, B. Sendhoff, and E. Körner. Evolution of hierarchical features for visual object recognition. In Horst-Michael Gross, Klaus Debes, and Hans-Joachim Boehme, editors, Third Workshop on SelfOrganization of AdaptiVE Behavior (SOAVE 2004) Ilmenau, pages 104-113. (PDF)
  
  
• G. Schneider, H. Wersing, B. Sendhoff, and E. Körner. Coupling of evolution and learning to optimize a hierarchical object recognition model. In X. Yao et al., editors, Parallel Problem Solving from Nature - PPSN VIII, pages 662-671. Springer, 2004. (PDF)
  
  
• G. Schneider, H. Wersing, B. Sendhoff, and E. Körner. Evolutionary feature design for object recognition with hierarchical networks. Proc. 9th International Conference on Neural Information Processing, ICONIP 2002, Singapore, pages (PDF)
  
  
• G. Brown, X. Yao, J. Wyatt, H. Wersing, B. Sendhoff. Exploiting Ensemble Diversity for Automatic Feature Extraction. Proc. 9th International Conference on Neural Information Processing, ICONIP 2002, Singapore. (PDF)

Feature binding, segmentation and perceptual grouping

• Heiko Wersing. Learning Lateral Interactions for Feature Binding and Sensory Segmentation. Advances in Neural Information Processing Systems NIPS 2001, Vancouver. pp. 1009-1016 (PDF)
  
  
• Heiko Wersing and Helge Ritter. Using maximal recurrence in linear threshold competitive layer networks. Proc. Int. Conf. on Art. Neur. Netw. ICANN 2001, Vienna, pages 799-805 (PDF)
  
  
• T. W. Nattkemper, H. Wersing, W. Schubert, and H. Ritter. Automatic Evaluation of Multi-Parameter Fluorescence Micrographs with a Neural Network Architecture Proc. of the Conf. on Mathematical and Engineering Techniques in Medical and Biological Sciences METMBS 2000 (4 pages, 0.3 MB gzipped Postscript).
  
  
• T. W. Nattkemper, H. Wersing, W. Schubert, and H. Ritter. Fluorescence Micrograph Segmentation by Gestalt-Based Feature Binding Proc. of the Int. Joint Conf. on Neur. Netw. IJCNN 2000 (7 pages, 0.1 MB gzipped Postscript).
  
  
• T. W. Nattkemper, H. Wersing, W. Schubert, and H. Ritter. A Neural Network Architecture for Automatic Segmentation of Fluorescence Micrographs. Proc. of the 8th Europ. Symp. on Art. Neur. Netw. ESANN 2000 pp. 177-182. (6 pages, 0.6 MB gzipped Postscript).
  
  
• Heiko Wersing and Helge Ritter. Backtracking deterministic annealing for constraint satisfaction problems. Proc. Int. Conf. on Art. Neur. Netw. ICANN 1999,  Edinburgh, pp 868-875. (6 pages, 0.1 MB gzipped Postscript).
  
  
• Heiko Wersing and Helge Ritter. Feature binding and relaxation labeling with the competitive layer model. Eur. Symp. on Art. Neur. Netw. ESANN 1999, Bruges, pages 295-300   (6 pages, 0.1 MB gzipped Postscript).
  
  
• Heiko Wersing, Jochen J. Steil, and Helge Ritter. A layered recurrent neural network for feature grouping. Proc. Int. Conf. on Art. Neur. Netw. ICANN 1997, Lausanne, pages 439-444 (6 pages, 0.2 MB gzipped Postscript)

Scientific activities

• Honorary Professor. Faculty of Technology, University of Bielefeld, Germany. (2017)
• Yearly Lecture on "Vision in Human and Machine". University of Bielefeld. (since 2009)
• Co-speaker Graduate School CoR-Lab Research Lab for Cognition and Robotics, University of Bielefeld, Germany (2007-2011)
• Program comittee International Conference on Artificial Neural Networks ICANN 2013, 2014, 2019
• Program committee European Symposium on Artificial Neural Networks ESANN 2007-2020 Bruges, Belgium.
• Program committee International Conference on Development and Learning ICDL 2011, Frankfurt, Germany
• Program committee Bernstein Conference on Computational Neuroscience 2009, Frankfurt, Germany.
• Program committee International Symposium on Imitation in Animals and Artifacts 2007 at the AISB'07 Convention in Newcastle upon Tyne, UK.
• Special session on online learning in cognitive robotics at ESANN 2006 (with J.J.Steil)

Prof. Dr. Heiko Wersing                           
Honda Research Institute Europe GmbH
Carl-Legien-Str. 30
63073 Offenbach /Main
Germany
Tel.: +49-69-89011741
Fax:  +49-69-89011749



 heiko (dot) wersing (at) honda-ri (dot) de