Logo des Repositoriums

Künstliche Intelligenz 26(4) - November 2012

https://dl.gi.de/handle/20.500.12116/11109
Auflistung nach:

Auflistung Künstliche Intelligenz 26(4) - November 2012 nach Schlagwort "Digit recognition"

1 - 1 von 1
  • Zeitschriftenartikel
    Sparse Coding and Selected Applications
    (KI - Künstliche Intelligenz: Vol. 26, No. 4, 2012) Hocke, Jens; Labusch, Kai; Barth, Erhardt; Martinetz, Thomas
    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 generalize 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.