Machine Learning

Python based source code of the 'Binary Sparse Coding (BSC)', 'Maximal Causes Analysis (MCA)'  and 'Spike-and-slab/Gaussian Sparse Coding (GSC)' algorithms are now available for download. The software packages implement MPI based parallelization and can be readily run on a single or multi-core/parallel architecture. Please see the corresponding 'Readme' files for more details about individual packages.

All the packages are available under the Academic Free License (AFL) v3.0.

 

GSC: [Gzip file, Readme]

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

 

BSC: [Gzip file, Readme]

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

 

MCA: [Gzip file, Readme]

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