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.
|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 status||Published - 01.01.2013|
|Event||9th Workshop on Self-Organizing Maps - Santiago, Santiago, Chile|
Duration: 12.12.2012 → 14.12.2012