Sparse Coding and Selected Applications

Jens Hocke, Kai Labusch, Erhardt Barth, Thomas Martinetz


Sparse coding has become a widely used framework in signal processing and pattern recognition. After a motivation of the principle of sparse coding we show the relation to Vector Quantization and Neural Gas and describe how this relation can be used to gen-eralize Neural Gas to successfully learn sparse coding dictionaries. We explore applications of sparse coding to image-feature extraction, image reconstruction and deconvolution, and blind source separation.
Original languageEnglish
Title of host publicationKI - Künstliche Intelligenz
Number of pages7
Publication date09.05.2012
ISBN (Print)4515005502
Publication statusPublished - 09.05.2012


Dive into the research topics of 'Sparse Coding and Selected Applications'. Together they form a unique fingerprint.

Cite this