direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

All Publications

Learning Quadratic Forms by Density Estimation and its Application to Image Coding
Citation key bart04
Author Bartsch, H. and Hochreiter, S. and Obermayer, K.
Year 2004
Journal Neurocomputing
Abstract We develop a novel method for source separation and apply it to natural images. It is a specialization of independent factor analysis (IFA) but overcomes generic IFA problems and finds many independent sources in few observations. A fast and robust EM learning algorithm produces an over-complete basis. Compared to standard approaches our method generates superior codes in terms of population sparseness and dispersity. The algorithm learns features which possess properties that are observed in simple as well as complex cells found in V1.
Link to original publication Download Bibtex entry

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe

Auxiliary Functions