Sparse Coding Neural Gas Applied to Image Recognition


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 languageEnglish
Title of host publicationAdvances in Self-Organizing Maps : 9th Workshop on Self-Organizing Maps
EditorsPablo A. Estévez, José C. Príncipe, Pablo Zegers
Number of pages10
PublisherSpringer Berlin Heidelberg
Publication date01.01.2013
ISBN (Print)978-3-642-35229-4
ISBN (Electronic)978-3-642-35230-0
Publication statusPublished - 01.01.2013
Event9th Workshop on Self-Organizing Maps - Santiago, Santiago, Chile
Duration: 12.12.201214.12.2012


Dive into the research topics of 'Sparse Coding Neural Gas Applied to Image Recognition'. Together they form a unique fingerprint.

Cite this