3 July 2020
We are looking for two new doctoral coworkers (PhD students) for our lab. Please see advertisement of the positions here.
30 June 2020
We have been granted access to large amounts of computing resources by the Northern German Network for HPC Computing (HLRN).
24 June 2020
Our paper on learning of higher-order statistics for image encoding (Mousavi, Drefs, Lücke, 2020) has been accepted by the International Conference on Machine Learning, Optimization, and Data Science.
20 May 2020
We have received top-up funding for the processing of SARS-CoV-2 EM microscopy images within our BMBF project SPAplus.
1 April 2020
Our project "SPAplus" (collaborative BMBF project, 3 years) has started. We will investigate medical image processing using generative models.
25 March 2020
Our paper "Phase transition for parameter learning of Hidden Markov Models" (Rau et al.) has been made available on arXiv.
15 March 2020
Our research activities shift to home offices due to the Corona crisis
4 March 2020
Our paper "Maximal Causes for Exponential Family Observables" (Mousavi et al.) has been made available on arXiv.
18 Feb 2020
Our abstract "Optimal Inference of Sound Intensities and Sound Components Using Generative Representations" (Monk, Savin, Lücke) has been accepted for the ASA Conference in Chicago, where it will be presented as a talk.
6 Feb 2020
Our project proposal "SPAplus" (collaborative BMBF project, 3 years) has been accepted and will be funded.
1 August 2019
Release of the open source software library "ProSper". The library contains a collection of algorithms for probabilistic sparse coding. For the source code see here. For a description see here.
2 April 2019
Our paper "k-Means as a Variational EM Approximation of Gaussian Mixture Models" was accepted for publication by Pattern Recognition Letters.
14-15 March 2019
Jörg Lücke gave a series of three lectures on Generative Machine Learning at the IK 2019 Spring School.
17 Jan 2019
Our paper "STRFs in primary auditory cortex emerge from masking-based statistics of natural sounds" (Sheikh et al.) has been published by PLOS Computational Biology.
16 July 2018
Our paper "Neural Simpletrons - Learning in the Limit of Few Labels with Directed Generative Networks" (Forster et al.) has been published by Neural Computation.
5 July 2018
Our paper "Truncated Variational Sampling for ‘Black Box’ Optimization of Generative Models" has been presented at the LVA/ICA 2018.
3 July 2018
Our paper "Optimal neural inference of stimulus intensities" (Monk et al.) has been published by Nature's Scientific Reports.
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.
Head of lab
Prof. Dr. Jörg Lücke
Arbeitsgruppe Machine Learning
Exzellenzcluster Hearing4all und
Department für Medizinische Physik und Akustik
Fakultät für Medizin und Gesundheitswissenschaften
Carl von Ossietzky Universität Oldenburg
Room 201 (2nd floor)
Building W30 (NeSSy)
Our aim is to learn as high quality classifiers from as few labels in total as possible, for the whole tuning and training procedure. To achieve this goal, we use generative networks of three layers based on normalized hierarchical Poisson mixture models: The first layer performing input data normalization, the second learning data clusters based on Poisson noise assumptions, and the third learning the cluster classes. The result are compact hebbian update rules which do not require labeled data for parameter optimization in the clustering layer and only a minimal amount of labels in the classification layer. We use self-labeling mechanisms and truncated approximations to further enhance the semi-supervised performance of the network. With only a handful of free parameters, small validation set sizes can be used for their optimization, reducing the total number of neccessary labels far below the standard sizes for deep networks. Typical application domains of the approach are hand-written symbols (MNIST, EMNIST etc.) and text document classification. Please see the papers listed below for more details.
Source code is available on GitHub.