Recognition of handwritten digits using sparse codes generated by local feature extraction methods
2006 (English)In: ESANN'2006: 14th European Symposium on Artificial Neural Networks, 2006, 161-166 p.Conference paper (Refereed)
We investigate when sparse coding of sensory inputs canimprove performance in a classification task. For this purpose, we use astandard data set, the MNIST database of handwritten digits. We systematicallystudy combinations of sparse coding methods and neural classifiersin a two-layer network. We find that processing the image data intoa sparse code can indeed improve the classification performance, comparedto directly classifying the images. Further, increasing the level of sparsenessleads to even better performance, up to a point where the reductionof redundancy in the codes is offset by loss of information.
Place, publisher, year, edition, pages
2006. 161-166 p.
IdentifiersURN: urn:nbn:se:kth:diva-6305ISBN: 2-930307-06-4OAI: oai:DiVA.org:kth-6305DiVA: diva2:10984
ESANN'2006 - European Symposium on Artificial Neural Networks. Bruges, Belgium. 26-28 April 2006
QC 201009162006-11-012006-11-012011-12-20Bibliographically approved