Research Group of Jörg Lücke

We study information processing and learning in computational and biological systems. We investigate such systems from the perspectives of Machine Learning and Computational Neuroscience. Each individual perspective answers important questions about the studied systems while their combination allows cross-fertilization and the development of integrated views.

Our main research focuses are unsupervised learning and computer vision. We pursue and conduct projects on non-linear component extraction, pattern recognition, and learning in neural circuits. Our probabilistic approaches aim to infer the often complex mechanisms that cause different types of data. We apply our models to data in computer vision, neuroscience, and different types of bio-medical data.

(for a full list of our publications, click here)

Z. Dai and J. Lücke (2012)
Autonomous Cleaning of Corrupted Scanned Documents - A Generative Modeling Approach
Proc. IEEE Computer Vision and Pattern Recognition (CVPR), accepted for oral presentation.

Z. Dai and J. Lücke (2012)
Unsupervised Learning of Translation Invariant Occlusive Components
Proc. IEEE Computer Vision and Pattern Recognition (CVPR), accepted. 

C. Keck^*, C. Savin^*, and J. Lücke (2012).
Feedforward Inhibition and Synaptic Scaling – Two Sides of the Same Coin? (online access, bibtex)
PLoS Computational 8(3): e1002432.
^*joint first authorship

J. A. Shelton, J. Bornschein, A.-S. Sheikh, P. Berkes, and J. Lücke (2011).
Select and Sample — A Model of Efficient Neural Inference and Learning (pdf, bibtex).
Advances in Neural Information Processing Systems 24, 2618-2626, 2011.

J. Lücke and J. Eggert (2010). 
Expectation Truncation and the Benefits of Preselection in Training Generative Models. (pdf, bibtex, animations, talk). 
Journal of Machine Learning Research 11:2855-2900, 2010.

G. Puertas^*, J. Bornschein^*, and J. Lücke (2010). 
The Maximal Causes of Natural Scenes are Edge Filters (pdf, bibtex, supplement, code). 
Advances in Neural Information Processing Systems 23, 1939-1947, 2010.
 ^*joint first authorship

J. Lücke (2009). 
Receptive Field Self-Organization in a Model of the Fine-Structure in V1 Cortical Columns (online access, bibtex). 
Neural Computation, 21(10):2805-2845.

J. Lücke, R. Turner, M. Sahani, and M. Henniges (2009). 
Occlusive Components Analysis (pdf, bibtex, supplementary). 
Advances in Neural Information Processing Systems 22, 1069-1077.

C. Möller, N. Arai, J. Lücke, and U. Ziemann (2009). 
Hysteresis Effects on the Input-Output Curve of Motor Evoked Potentials (pdf, bibtex). 
Clinical Neurophysiology 120(5):1003--1008.

P. Wolfrum, C. Wolff, J. Lücke, and C. von der Malsburg (2008). 
A Recurrent Dynamic Model for Correspondence-Based Face Recognition (pdf, bibtex). 
Journal of Vision 8(7):34, 1-18. 

J. Lücke and M. Sahani (2008). 
Maximal Causes for Non-linear Component Extraction (pdf, bibtex). 
Journal of Machine Learning Research 9:1227-1267. 

J. Lücke, C. Keck, and C. von der Malsburg (2008). 
Rapid Convergence to Feature Layer Correspondences. (preprint, bibtex, doi). 
Neural Computation 20(10):2441-2463.

The papers listed above have been published after peer review in different journals. These journals remain the only definitive repository of the content. Copyright and all rights therein are usually retained by the respective publishers. These materials may not be copied or reposted without their explicit permission. Use for scholarly purposes only.