Sparse Coding and Selected Applications

Jens Hocke; Kai Labusch; Erhardt Barth; Thomas Martinetz

doi:10.1007/s13218-012-0197-0

Sparse Coding and Selected Applications

Jens Hocke, Kai Labusch, Erhardt Barth, Thomas Martinetz

Institut für Neuro- und Bioinformatik

2 Zitate (Scopus)

Abstract

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.

Originalsprache	Englisch
Titel	KI - Künstliche Intelligenz
Seitenumfang	7
Erscheinungsdatum	09.05.2012
Seiten	349-355
ISBN (Print)	4515005502
DOIs	https://doi.org/10.1007/s13218-012-0197-0
Publikationsstatus	Veröffentlicht - 09.05.2012

UN SDGs

Dieser Output leistet einen Beitrag zu folgendem(n) Ziel(en) für nachhaltige Entwicklung

SDG 3 – Gesundheit und Wohlergehen
SDG 9 – Industrie, Innovation und Infrastruktur

Dokumente

10.1007/s13218-012-0197-0

HoLaBaMa12Endgültige, publizierte Fassung (Verlagsversion), 948 KB

Weitere Links

http://www.mendeley.com/research/sparse-coding-selected-applications

1 Abgeschlossen

SPP 1527, Teilprojekt: Lernen effizienter Abtastung für das aktive Sehen
Martinetz, T. (Sprecher*in) & Barth, E. (Beteiligte*r Wissenschaftler*in)
01.10.11 → 30.09.16
Projekt: DFG Verbundprojekte › DFG Schwerpunktprogramme (SPP)

Zitieren

@inbook{d331f6feeda34d09a998cb6fe625be17,

title = "Sparse Coding and Selected Applications",

abstract = "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.",

author = "Jens Hocke and Kai Labusch and Erhardt Barth and Thomas Martinetz",

year = "2012",

month = may,

day = "9",

doi = "10.1007/s13218-012-0197-0",

language = "English",

isbn = "4515005502",

series = "KI - K{\"u}nstliche Intelligenz",

pages = "349--355",

booktitle = "KI - K{\"u}nstliche Intelligenz",

}

TY - CHAP

T1 - Sparse Coding and Selected Applications

AU - Hocke, Jens

AU - Labusch, Kai

AU - Barth, Erhardt

AU - Martinetz, Thomas

PY - 2012/5/9

Y1 - 2012/5/9

N2 - 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.

AB - 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.

UR - http://www.mendeley.com/research/sparse-coding-selected-applications

U2 - 10.1007/s13218-012-0197-0

DO - 10.1007/s13218-012-0197-0

M3 - Chapter

SN - 4515005502

T3 - KI - Künstliche Intelligenz

SP - 349

EP - 355

BT - KI - Künstliche Intelligenz

ER -

Sparse Coding and Selected Applications

Abstract

UN SDGs

Dokumente

Weitere Links

Fingerprint

Projekte

SPP 1527, Teilprojekt: Lernen effizienter Abtastung für das aktive Sehen

Zitieren