D. Velychko, S. Damm, Z. Dai, A. Fischer and J. Lücke (2024).
Learning Sparse Codes with Entropy-Based ELBOs.
Int. Conf. on Artificial Intelligence and Statistics (AISTATS), 2024. (pdf, bibtex)

H. Mousavi, J. Drefs, F. Hirschberger, J. Lücke (2023).
Generic Unsupervised Optimization for a Latent Variable Model with Exponential Family Observables.
Journal of Machine Learning Research 24(285):1−59. (online access, bibtex)

S. Damm*, D. Forster, D. Velychko, Z. Dai, A. Fischer and J. Lücke* (2023).
The ELBO of Variational Autoencoders Converges to a Sum of Entropies.
Int. Conf. on Artificial Intelligence and Statistics (AISTATS), 3931-3960, 2023. (online access, bibtex).
*joint main contributions

J. Drefs*, E. Guiraud*, F. Panagiotou, J. Lücke (2023).
Direct Evolutionary Optimization of Variational Autoencoders With Binary Latents.
European Conference on Machine Learning, 357-372. (pdf, bibtex).
*joint first authorship

F. Hirschberger*, D. Forster* and J. Lücke (2022).
A Variational EM Acceleration for Efficient Clustering at Very Large Scales.
IEEE Transactions on Pattern Analysis and Machine Intelligence 44(12):9787-9801 (online access, bibtex).
*joint first authorship.

J. Drefs, E. Guiraud and J. Lücke (2022).
Evolutionary Variational Optimization of Generative Models.
Journal of Machine Learning Research 23(21):1-51 (online access, bibtex).

N. Rau, J. Lücke, and A. Hartmann (2021).
Phase transition for parameter learning of hidden Markov models.
Phys. Rev. E 104(4): 044105 (online access)

M. Boos, J. Lücke and J. W. Rieger (2021).
Generalizable dimensions of human cortical auditory processing of speech in natural soundscapes: A data-driven ultra high field fMRI approach.
NeuroImage 237: 118106 (online access, bibtex)

H. Mousavi, M. Buhl, E. Guiraud, J. Drefs, and J. Lücke (2021).
Inference and learning in a latent variable model for beta distributed interval data.
Entropy 23(5) (online access, bibtex)

J. Drefs, S. Salwig, J. Lücke (2021).
Visualization of SARS-CoV-2 Infection Scenes by ‘Zero-Shot’ Enhancements of Electron Microscopy Images.
bioRxiv 2021.02.25.432265 (biorxiv)

S. H. Mousavi*, J. Drefs*, J. Lücke (2020).
A Double-Dictionary Approach Learns Component Means and Variances for V1 Encoding.
The Sixth International Conference on Machine Learning, Optimization, and Data Science (LOD), 240-244. (online access, bibtex) 
*joint first authorship.

S. H. Mousavi, J. Drefs, F. Hirschberger, J. Lücke (2020).
Maximal Causes for Exponential Family Observables.
arXiv:2003.02214 (arXiv)

J. Lücke and D. Forster (2019).
k-means as a variational EM approximation of Gaussian mixture models.
Pattern Recognition Letters 125:349-356 (online access, bibtex, arXiv)

A. S. Sheikh*, N. S. Harper*, J. Drefs, Y. Singer, Z. Dai, R. E. Turner and J. Lücke (2019).
STRFs in primary auditory cortex emerge from masking-based statistics of natural sounds.
PLOS Computational Biology 15(1): e1006595 (online access, bibtex)
*joint first authorship.

T. Monk, C. Savin and J. Lücke (2018).
Optimal neural inference of stimulus intensities.
Scientific Reports 8: 10038 (online access, bibtex)

E. Guiraud, J. Drefs and J. Lücke, (2018).
Evolutionary Expectation Maximization.
Genetic and Evolutionary Computation Conference (GECCO), (online access , bibtex)

J. Lücke, Z. Dai and G.Exarchakis (2018).
Truncated Variational Sampling for ‘Black Box’ Optimization of Generative Models.
International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA), 10891: 467-478. (online access, bibtex)

D. Forster, A.-S. Sheikh and J. Lücke (2018).
Neural Simpletrons - Learning in the Limit of Few Labels with Directed Generative Networks
Neural Computation 30:2113–2174 (online access, bibtex)

D. Forster and J. Lücke (2018).
Can clustering scale sublinearly with its clusters? A variational EM acceleration of GMMs and k-means.
International Conference on Artificial Intelligence and Statistics (AISTATS), 84:124-132. (online access)

G. Exarchakis and J. Lücke (2017).
Discrete Sparse Coding.
Neural Computation 29(11):2979-3013. (online access, bibtex)

R. Holca-Lamarre, J. Lücke* and K. Obermayer* (2017).
Models of Acetylcholine and Dopamine Signals Differentially Improve Neural Representations.
Frontiers in Computational Neuroscience 11:54 (online access, bibtex)
*joint senior authorship.

J. A. Shelton, J. Gasthaus, Z. Dai, J. Lücke and A. Gretton (2017).
GP-select: Accelerating EM using adaptive subspace preselection.
Neural Computation 29(8):2177-2202. (online access, bibtex)

S. Drgas, T. Virtanen, J. Lücke and A. Hurmalainen (2017).
Binary non-negative matrix deconvolution for audio dictionary learning.
IEEE/ACM Transactions on Audio, Speech and Language Processing 25: 1644-1656. (online access, bibtex)

D. Forster and J. Lücke (2017).
Truncated Variational EM for Semi-Supervised Neural Simpletrons.
International Joint Conference for Neural Networks (IJCNN), 3769-3776. (arXiv version, bibtex)

A.-S. Sheikh and J. Lücke (2016).
Select-and-Sample for Spike-and-Slab Sparse Coding.
Advances in Neural Information Processing Systems (NIPS) 29: 3927-3935. (online access, bibtex)

T. Monk, C. Savin and J. Lücke (2016).
Neurons Equipped with Intrinsic Plasticity Learn Stimulus Intensity Statistics.
Advances in Neural Information Processing Systems (NIPS) 29: 4278-4286. (online access, bibtex)

J. Thiemann, J. Lücke and S. van de Par (2016).
Speaker Tracking for Hearing Aids.
IEEE Int. Workshop on Machine Learning for Signal Processing, 26: 1-6 (online access, bibtex).

F. Hutter, J. Lücke and Lars Schmidt-Thieme (2015).
Beyond Manual Tuning of Hyperparameters
Künstliche Intelligenz 29(4): 329-337. (online access, bibtex)

J.A. Shelton, A.-S. Sheikh, J. Bornschein, P. Sterne and J. Lücke (2015).
Nonlinear Spike-and-slab Sparse Coding for Interpretable Image Encoding
PLoS One 10(5): e0124088 (online access, bibtex)

M. Henniges, R. E. Turner, M. Sahani, J. Eggert and J. Lücke (2014).
Efficient Occlusive Components Analysis.
Journal of Machine Learning Research, 15:2689-2722. (online access, bibtex)

A.-S. Sheikh, J. A. Shelton and J. Lücke (2014).
A Truncated EM Approach for Spike-and-Slab Sparse Coding.
Journal of Machine Learning Research, 15:2653-2687. (online access, bibtex)

Z. Dai and J. Lücke (2014).
Autonomous Document Cleaning – A Generative Approach to Reconstruct Strongly Corrupted Scanned Texts.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(10): 1950-1962. (online access, bibtex)

C.-M. Svensson, S. Krusekopf, J. Lücke and M. T. Figge (2014).
Automated Detection of Circulating Tumour Cells With Naive Bayesian Classifiers.
Cytometry Part A, 85(6): 501-511. (online access, bibtex)

Z. Dai, G. Exarchakis and J. Lücke (2013).
What Are the Invariant Occlusive Components of Image Patches? A Probabilistic Generative Approach.
Advances in Neural Information Processing Systems 26:243-251. (online access, bibtex)

J. Bornschein, M. Henniges and J. Lücke (2013).
Are V1 simple cells optimized for visual occlusions? A comparative study.
PLOS Computational Biology, 9(6): e1003062. (online access, bibtex)

J. A. Shelton, P. Sterne, J. Bornschein, A.-S. Sheikh and J. Lücke (2012).
Why MCA? Nonlinear sparse coding with spike-and-slab prior for neurally plausible image encoding.
Advances in Neural Information Processing Systems 25:2285-2293. (online access, bibtex)

Z. Dai and J. Lücke (2012)
Autonomous Cleaning of Corrupted Scanned Documents - A Generative Modeling Approach.
Proc. IEEE Computer Vision and Pattern Recognition (CVPR), 3338-3345, oral presentation.
(highest CVPR 2012 reviewer score and Google Student Travel Award) (arXiv version, bibtex)

Z. Dai and J. Lücke (2012).
Unsupervised Learning of Translation Invariant Occlusive Components.
Proc. IEEE Computer Vision and Pattern Recognition (CVPR), 2400-2407. (online access, bibtex)

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

G. Exarchakis, M. Henniges, J. Eggert and J. Lücke (2012).
Ternary Sparse Coding .
International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA), 204-212. (online acces, bibtex)

J. Lücke* and A.-S. Sheikh* (2012).
A Closed-Form EM Algorithm for Sparse Coding and Its Application to Source Separation.
International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA), 213-221. (online access, bibtex, code)
*joint first authorship.

J. Lücke and M. Henniges (2012).
Closed-Form Entropy Limits – A Tool to Monitor Likelihood Optimization of Probabilistic Generative Models.
AI & Statistics (AISTATS 15), 731-740. (online access, bibtex)

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.
Advances in Neural Information Processing Systems 24, 2618-2626. (online access, bibtex)

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

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

M. Henniges, G. Puertas, J. Bornschein, J. Eggert and J. Lücke (2010).
Binary Sparse Coding.
Proc. LVA/ICA 2010, LNCS 6365, 450-457. (pdf, bibtex, code)

C. Keck and J. Lücke (2010).
Learning of Lateral Connections for Representational Invariant Recognition.
Proc. ICANN 2010, LNCS 6354, 21-30. (pdf, bibtex)

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

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

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

J. D. Bouecke and J. Lücke (2008).
Learning of Neural Information Routing for Correspondence Finding .
Proc. ICANN, LNCS 5164, Part II, 557-566, Springer. (online access, bibtex)

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

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

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

J. Lücke and M. Sahani (2007).
Generalized Softmax Networks for Non-Linear Component Extraction.
Proc. ICANN, LNCS 4668, 657-667, Springer. (online access, bibtex)

J. Lücke (2007).
A Dynamical Model for Receptive Field Self-Organization in V1 Cortical Columns.
Proc. ICANN, LNCS 4669, 389-398, Springer. (online access, bibtex)

C. Möller, J. Lücke, J. Zhu, P. M. Faustmann and C. von der Malsburg (2007).
Glial Cells for Information Routing?
Cognitive Systems Research, 8:28-35. (pdf, bibtex)

J. Lücke and C. von der Malsburg (2006).
Rapid Correspondence Finding in Networks of Cortical Columns.
Proc. ICANN, LNCS 4131, 668-677, Springer. (online access, bibtex)

J. Lücke and J. D. Bouecke (2005).
Dynamics of Cortical Columns - Self-Organization of Receptive Fields.
Proc. ICANN, LNCS 3696, 31-37, Springer. (online access, bibtex)

J. Lücke (2005).
Dynamics of Cortical Columns - Sensitive Decision Making.
Proc. ICANN, LNCS 3696, 25-30, Springer. (online access, bibtex)

J. Lücke (2004).
Hierarchical self-organization of minicolumnar receptive fields .
Neural Networks 17, 1377-1389. (online access, bibtex)

J. Lücke (2004).
Clustering with minicolumnar receptive field self-organization.
Proc. IJCNN, IEEE/Omnipress, 3113-3118. (online access, bibtex)

J. Lücke and C. von der Malsburg (2004).
Rapid processing and unsupervised learning in a model of the cortical macrocolumn.
Neural Computation, 16(3), 501-533. (online access, bibtex)

J. Lücke, C. von der Malsburg and R. P. Würtz (2002).
Macrocolumns as Decision Units.
Proc. ICANN, LNCS 2415, 57-62, Springer. (online access, bibtex)

J. Lücke (2001).
Hilberticus - a Tool Deciding an Elementary Sublanguage of Set Theory.
Proc. IJCAR, LNCS/LNAI, 2083, 690–695, Springer. (online access, bibtex)

J. Lücke (2005). 
Information Processing and Learning in Networks of Cortical Columns (contents, link to publisher, bibtex, pdf). 
Shaker Verlag, ISBN 3-8322-3966-9, Dissertation. (For related work, please see PDFs above.) 

Cristina Savin, Travis Monk, Jörg Lücke (2016).
Intrinsic plasticity for optimal learning of variable stimulus intensities.
Proc. Computational and Systems Neuroscience (COSYNE), III-29.

Birger Kollmeier, Thomas Lenarz, Anna Warzybok, Marc R. Schädler, Sabine Haumann, Thomas Brand and Jörg Lücke (2016).
Auditory profile and common audiological functional parameters (CAFPAs): From diagnostics to machine-learning-based evidence.
Association for Research In Otolaryngology Meeting (ARO).

Raphael Holca-Lamarre, Klaus Obermayer and Jörg Lücke (2015).
A Model of Perceptual Learning: From Neuromodulation to Improved Performance.
Proc. Computational and Systems Neuroscience (COSYNE), III-12.

Abdul-Saboor Sheikh, Zhenwen Dai, Nicol Harper, Richard Turner and Jörg Lücke (2015).
Maximal causes for a masking based model of STRFs in primary auditory cortex.
Proc. Computational and Systems Neuroscience (COSYNE), II-47.

J. A. Shelton, A.-S. Sheikh, P. Sterne, J. Bornschein and J. Lücke (2013).
Nonlinear spike-and-slab sparse coding for interpretable image encoding.
Extended Abstract, NIPS Workshop on High-Dimensional Statistical Inference in the Brain.

J. Lücke, J. A. Shelton, P. Sterne, P. Berkes, J. Bornschein and A.-S. Sheikh (2013).
Combining Feed-Forward Processing and Sampling for Neurally Plausible Encoding Models.
Computational and Systems Neuroscience, poster III-28.

D. Forster, A.-S. Sheikh and J. Lücke (2013). 
Efficient Classification by a Neural Network Approximation of Hierarchical Poisson Mixtures.
Bernstein Conference 2013. doi: 10.12751/nncn.bc2013.0147

Z. Dai, J. Shelton, J. Bornschein, A.-S. Sheikh and J. Lücke (2011).
Combining approximate inference methods for efficient learning on large computer clusters (abstract, poster). 
Extended Abstract, NIPS Workshop: Big Learning.

J. Bornschein, M. Henniges, G. Puertas and J. Lücke (2011).
Sparse codes of V1 simple-cells and the emergence of globular receptive fields – a comparative study
Proc. COSYNE. (abstract, poster) 

C. Keck, C. Savin and J. Lücke (2011).
Input normalization and synaptic scaling - two sides of the same coin (abstract, poster)
Proc. COSYNE. 

Z. Dai and J. Lücke (2010).  
A Probabilistic Generative Approach to Invariant Visual Inference and Learning  
Frontiers Comp Neurosci, Proceedings BCCN. (abstract, poster, online access) 

J. Bornschein, Z. Dai and J. Lücke (2010).  
Approximate EM Learning on Large Computer Clusters (extended abstract, poster) 
Extended Abstract, NIPS Workshop: Learning on Cores, Clusters and Clouds. 

J. Bornschein, M. Henniges, G. Puertas and J. Lücke (2010)  
Binary Hidden Variables and Sparse Sensory Coding  
Frontiers Comp Neurosci, Proceedings BCCN. (online access)

J. Bornschein and J. Lücke (2009). 
Applications of Non-linear Component Extraction to Spectrogram Representations Of Auditory Data 
Frontiers in Compuational Neuroscience, Proc. BCCN (poster, online access). 

C. Keck, J. D. Bouecke and J. Lücke (2009). 
Learning of Lateral Connections for Representational Invariant Recognition 
Frontiers in Compuational Neuroscience, Proc. BCCN (online access).

C. Möller, N. Arai, J. Lücke and U. Ziemann (2009). 
Hysteresis Effects of Cortico-Spinal Excitability During TMS Stimulation 
Frontiers in Compuational Neuroscience, Proc. BCCN (online access).

J. Lücke and M. Sahani (2007). 
Learning in a Generative Model with Competitive Combination Is Approximated by (Soft-)WTA Networks 
Proc. COSYNE.

J. Lücke, C. Keck, P. Wolfrum, C. Wolff, J. D. Bouecke and C. von der Malsburg (2007). 
Neural Feature Layers Can Establish Correspondences In Physiological Time 
Proc. COSYNE.

J. Lücke (2006). 
Learning of Representations in a Canonical Model of Cortical Columns 
Proc. COSYNE.

J. Lücke (2005). 
Dynamics of Cortical Macrocolumns - An Abstract Derivation. 
Proc. COSYNE.
 

M. Henniges (2013).
Unsupervised Learning in Generative Models of Occlusion.
Dissertationsschrift, Fachbereich Physik, Goethe-Universität Frankfurt am Main.
PhD Thesis, Dept of Physics, Goethe-University Frankfurt am Main.

Z. Dai (2013).
Unsupervised Learning of Invariant Object Representations - A Probabilistic Generative Modeling Approach.
Dissertationsschrift, Fachbereich Informatik und Mathematik, Goethe-Universität Frankfurt am Main.
PhD Thesis, Dept of Computer Science and Mathematics, Goethe-University Frankfurt am Main.

C. Keck (2013).
Models for correspondence finding and representative learning.
Dissertationsschrift, Fakultät für Elektrotechnik und Informationstechnik, Ruhr-Universität Bochum.
PhD Thesis, Dept of Electrical Engineering and Information Technology, Ruhr-University Bochum.

J. Bornschein (2013).
Large-scale parallelized learning of nonlinear sparse coding models.
Dissertationsschrift, Fachbereich Informatik und Mathematik, Goethe-Universität Frankfurt am Main.
PhD Thesis, Dept of Computer Science and Mathematics, Goethe-University Frankfurt am Main.