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)
Software is available for three areas of research:
Different algorithms using variational acceleration are available. The algorithms are basically applicable to any data where k-means is expected to work well. Results of k-means are usually improved upon in quality, speed or both. Improvements in quality can especially be expected for data with large overlap. Improvements in speed will be observed especially for large scale data, i.e., data with large data spaces, many data points and many clusters. In these cases speedups can be one or two orders of magnitude.
Sparse Coding algorithms aim at extracting the elementary constituents of data. We make available a range of algorithms which assume binary, discrete or a combination of binary-continuous constituents for data generation. As customary, the data is assumed continuous.
We offer an algorithm based on a generative neural network which allows for learning from large datasets with few labels. The aim is to learn as high quality classifiers from few labels as possible. Typical application domains of the approach are hand-written symbols (MNIST, NIST etc) and text document classification.