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

• 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.

Ämnesord

NATURVETENSKAP  -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)

NATURAL SCIENCES  -- Computer and Information Sciences -- Computer Sciences (hsv//eng)

Nyckelord

Computer science

Datalogi

Publikations- och innehållstyp

ref (ämneskategori)

kon (ämneskategori)