Sparse Coding Neural Gas Applied to Image Recognition

Horia Coman; Erhardt Barth; Thomas Martinetz

doi:10.1007/978-3-642-35230-0_11

Sparse Coding Neural Gas Applied to Image Recognition

Horia Coman, Erhardt Barth, Thomas Martinetz

Institute of Neuro- and Bioinformatics

University POLITEHNICA of Bucureşti

Abstract

A generalization of the Sparse Coding Neural Gas (SCNG) algorithm for feature learning is proposed and is then discussed in the context of modern classifier techniques for images. Two versions are presented. The latter obtains faster convergence by exploiting the nature of particular feature coding methods. The algorithm is then used as part of a larger image classification system, which is tested on the MNIST handwritten digit dataset and the NORB object dataset, obtaining results close to state-of-the-art methods.

Original language	English
Title of host publication	Advances in Self-Organizing Maps : 9th Workshop on Self-Organizing Maps
Editors	Pablo A. Estévez, José C. Príncipe, Pablo Zegers
Number of pages	10
Publisher	Springer Berlin Heidelberg
Publication date	01.01.2013
Pages	105-114
ISBN (Print)	978-3-642-35229-4
ISBN (Electronic)	978-3-642-35230-0
DOIs	https://doi.org/10.1007/978-3-642-35230-0_11
Publication status	Published - 01.01.2013
Event	9th Workshop on Self-Organizing Maps - Santiago, Santiago, Chile Duration: 12.12.2012 → 14.12.2012 http://www.die.uchile.cl/wsom2012/

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-642-35230-0_11

Cite this

Coman, H., Barth, E., & Martinetz, T. (2013). Sparse Coding Neural Gas Applied to Image Recognition. In P. A. Estévez, J. C. Príncipe, & P. Zegers (Eds.), Advances in Self-Organizing Maps: 9th Workshop on Self-Organizing Maps (pp. 105-114). (Advances in Intelligent Systems and Computing; Vol. Vol. 198). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-642-35230-0_11

@inproceedings{77dbc280436e4318a36112666c5da4d1,

title = "Sparse Coding Neural Gas Applied to Image Recognition",

abstract = "A generalization of the Sparse Coding Neural Gas (SCNG) algorithm for feature learning is proposed and is then discussed in the context of modern classifier techniques for images. Two versions are presented. The latter obtains faster convergence by exploiting the nature of particular feature coding methods. The algorithm is then used as part of a larger image classification system, which is tested on the MNIST handwritten digit dataset and the NORB object dataset, obtaining results close to state-of-the-art methods.",

author = "Horia Coman and Erhardt Barth and Thomas Martinetz",

year = "2013",

month = jan,

day = "1",

doi = "10.1007/978-3-642-35230-0_11",

language = "English",

isbn = "978-3-642-35229-4",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer Berlin Heidelberg",

pages = "105--114",

editor = "Est{\'e}vez, {Pablo A. } and Pr{\'i}ncipe, {Jos{\'e} C. } and Zegers, {Pablo }",

booktitle = "Advances in Self-Organizing Maps",

note = "9th Workshop on Self-Organizing Maps ; Conference date: 12-12-2012 Through 14-12-2012",

url = "http://www.die.uchile.cl/wsom2012/",

}

Coman, H, Barth, E & Martinetz, T 2013, Sparse Coding Neural Gas Applied to Image Recognition. in PA Estévez, JC Príncipe & P Zegers (eds), Advances in Self-Organizing Maps: 9th Workshop on Self-Organizing Maps. Advances in Intelligent Systems and Computing, vol. Vol. 198, Springer Berlin Heidelberg, pp. 105-114, 9th Workshop on Self-Organizing Maps, Santiago, Chile, 12.12.12. https://doi.org/10.1007/978-3-642-35230-0_11

Sparse Coding Neural Gas Applied to Image Recognition. / Coman, Horia; Barth, Erhardt ; Martinetz, Thomas.
Advances in Self-Organizing Maps: 9th Workshop on Self-Organizing Maps. ed. / Pablo A. Estévez; José C. Príncipe; Pablo Zegers. Springer Berlin Heidelberg, 2013. p. 105-114 (Advances in Intelligent Systems and Computing; Vol. Vol. 198).

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - Sparse Coding Neural Gas Applied to Image Recognition

AU - Coman, Horia

AU - Barth, Erhardt

AU - Martinetz, Thomas

PY - 2013/1/1

Y1 - 2013/1/1

N2 - A generalization of the Sparse Coding Neural Gas (SCNG) algorithm for feature learning is proposed and is then discussed in the context of modern classifier techniques for images. Two versions are presented. The latter obtains faster convergence by exploiting the nature of particular feature coding methods. The algorithm is then used as part of a larger image classification system, which is tested on the MNIST handwritten digit dataset and the NORB object dataset, obtaining results close to state-of-the-art methods.

AB - A generalization of the Sparse Coding Neural Gas (SCNG) algorithm for feature learning is proposed and is then discussed in the context of modern classifier techniques for images. Two versions are presented. The latter obtains faster convergence by exploiting the nature of particular feature coding methods. The algorithm is then used as part of a larger image classification system, which is tested on the MNIST handwritten digit dataset and the NORB object dataset, obtaining results close to state-of-the-art methods.

UR - http://www.die.uchile.cl/wsom2012/

UR - https://link.springer.com/chapter/10.1007/978-3-642-35230-0_11

U2 - 10.1007/978-3-642-35230-0_11

DO - 10.1007/978-3-642-35230-0_11

M3 - Conference contribution

SN - 978-3-642-35229-4

T3 - Advances in Intelligent Systems and Computing

SP - 105

EP - 114

BT - Advances in Self-Organizing Maps

A2 - Estévez, Pablo A.

A2 - Príncipe, José C.

A2 - Zegers, Pablo

PB - Springer Berlin Heidelberg

T2 - 9th Workshop on Self-Organizing Maps

Y2 - 12 December 2012 through 14 December 2012

ER -

Sparse Coding Neural Gas Applied to Image Recognition

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this