Sciweavers

Share
ESANN
2006

Recognition of handwritten digits using sparse codes generated by local feature extraction methods

9 years 1 months ago
Recognition of handwritten digits using sparse codes generated by local feature extraction methods
We investigate when sparse coding of sensory inputs can improve performance in a classification task. For this purpose, we use a standard data set, the MNIST database of handwritten digits. We systematically study combinations of sparse coding methods and neural classifiers in a two-layer network. We find that processing the image data into a sparse code can indeed improve the classification performance, compared to directly classifying the images. Further, increasing the level of sparseness leads to even better performance, up to a point where the reduction of redundancy in the codes is offset by loss of information.
Rebecca Steinert, Martin Rehn, Anders Lansner
Added 31 Oct 2010
Updated 31 Oct 2010
Type Conference
Year 2006
Where ESANN
Authors Rebecca Steinert, Martin Rehn, Anders Lansner
Comments (0)
books