Machine Learning

Our Research

Based on first theoretical principles, our group develops novel efficient learning algorithms for standard and novel data models. The resulting algorithms are then applied to a range of different domains including acoustic data, visual data, medical data and data of general pattern recognition tasks. Alongside these theoretical and practical algorithm development, we investigate advanced Machine Learning methods as models for neural information processing; and, visa versa, use ideas and insights from the neurosciences to motivate novel research directions in Machine Learning.

We pursue and conduct projects on non-linear dictionary learning, large-scale unsupervised and semi-supervised learning, and autonomous learning.

We are part of the cluster of excellence Hearing4all and the Department of Medical Physics and Acoustics at the School of Medicine and Health Sciences.

For any inquiries please contact Jörg Lücke.

Selected Recent Publications

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), in press (online access)

D. Forster, A.-S. Sheikh and J. Lücke (2018).
Neural Simpletrons - Learning in the Limit of Few Labels with Directed Generative Networks
Neural Computation, in press.

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 accessbibtex)
*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 accessbibtex)

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

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 accessbibtex)

A.-S. Sheikh and J. Lücke (2016).
Select-and-Sample for Spike-and-Slab Sparse Coding.
Advances in Neural Information Processing Systems (NIPS), 29: 3934-3942. (online accessbibtex)

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)

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

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

COPYRIGHT NOTICE

The papers listed above have been published after peer review in different journals or conference proceedings. These journals or proceedings 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.

 

News

  • 24 March 2018
    Our paper "Evolutionary Expectation Maximization" (Guiraud et al.) has been accepted for GECCO 2018.

  • 19 March 2018
    Our paper "Truncated Variational Sampling for ‘Black Box’ Optimization of Generative Models" (Lücke et al.) has been accepted for LVA/ICA 2018.

  • 5 March 2018
    Our paper "Neural Simpletrons - Learning in the Limit of Few Labels with Directed Generative Networks" (Forster et al.) has been accepted by Neural Computation.

  • 22 Dec 2017
    Our paper "Can clustering scale sublinearly with its clusters?" (Forster & Lücke) has been accepted for AISTATS 2018.

  • 30 June 2017
    Our paper "Discrete Sparse Coding" (Exarchakis & Lücke) has been accepted by Neural Computation.

  • 7 June 2017
    Our paper "Models of acetylcholine and dopamine signals differentially improve neural representations" (Holca-Lamarre et al.) has been accepted by the journal Frontiers in Neuroscience.

  • 25 May 2017
    Our paper "Binary non-negative matrix deconvolution for audio dictionary learning" (Drgas et al.) has been accepted by the journal IEEE Transactions on Audio, Speech and Language Processing.

  • 8 Mar 2017
    Our paper "GP-select: Accelerating EM using adaptive subspace preselection" (Shelton et al.) has been accepted for publication by Neural Computation.

  • 4 Feb 2017
    Our paper "Truncated Variational EM for Semi-Supervised Neural Simpletrons" (Forster & Lücke) has been accepted for the IJCNN 2017 conference.

  • 9 Dec 2016
    Jörg Lücke gave the talk "Probabilistic Inference and the Brain: Towards General, Scalable, and Deep Approximations" at the NIPS Workshop "Brains and Bits"

  • 9 Dec 2016
    We presented three posters about our research at the NIPS Workshop "Brains and Bits"

  • 8 Dec 2016
    Our Paper ""Select-and-Sample for Spike-and-Slab Sparse Coding." (Sheikh & Lücke) was presented at the NIPS 2016 main conference.

  • 5 Dec 2016
    Our Paper "Neurons Equipped with Intrinsic Plasticity Learn Stimulus Intensity Statistics." (Monk et al.) was presented at the NIPS 2016 main conference.

  • 1 Dec 2016
    Georgios Exarchakis successfully defended his PhD Thesis. Congratulations!

  • 16 Nov 2016
    Enrico Guiraud starts his joint PhD project with our group and CERN (his main work place).

  • 14 Nov 2016
    Abdul-Saboor Sheikh successfully defended his PhD Thesis. Congratulations!

  • 12 Aug 2016
    Our paper "Select-and-Sample for Spike-and-Slab Sparse Coding." (Sheikh & Lücke) is accepted for the NIPS 2016 main conference.

  • 12 Aug 2016
    Our paper "Neurons Equipped with Intrinsic Plasticity Learn Stimulus Intensity Statistics." (Monk et al.) is accepted for the NIPS 2016 main conference.

  • 10-11 Aug 2016
    The international workshop "New Algorithms and Tools for Probabilistic Machine Learning" takes place at the Machine Learning Lab at Oldenburg University. Thanks to all developers and contributors!

  • 8-9 Aug 2016
    The international symposium "Advanced Machine Learning Methods for Pattern Recognition and Sensory Data Analysis" takes place in the NeSSy research building of Oldenburg University. Thanks to all speakers and participants!

  • 5 July 2016
    The paper "Speaker Tracking for Hearing Aids" (Thiemann et al.) is accepted for the IEEE International Workshop on Machine Learning for Signal Processing.

  • 2 June 2016
    Joanna Luberadzka has successfully defended her Master thesis in Hearing Technology and Audiology. Congratulations!

  • 16 May 2016
    Hamid Mousavi (MSc in Optimization) has joined the group as a PhD student.

  • 27 Feb 2016
    Our abstract by Savin et al. about optimal coding and intrinsic plasticity is presented at the COSYNE conference.