Search: id:"swepub:oai:DiVA.org:kth-6305" >
Recognition of hand...
-
Steinert, RebeccaKTH,Numerisk Analys och Datalogi, NADA,Beräkningsbiologi, CB
(author)
Recognition of handwritten digits using sparse codes generated by local feature extraction methods
- Article/chapterEnglish2006
Publisher, publication year, extent ...
Numbers
-
LIBRIS-ID:oai:DiVA.org:kth-6305
-
https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-6305URI
Supplementary language notes
-
Language:English
-
Summary in:English
Part of subdatabase
Classification
-
Subject category:ref swepub-contenttype
-
Subject category:kon swepub-publicationtype
Notes
-
QC 20100916
-
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.
Subject headings and genre
Added entries (persons, corporate bodies, meetings, titles ...)
-
Rehn, MartinKTH,Numerisk Analys och Datalogi, NADA(Swepub:kth)u1n8grvo
(author)
-
Lansner, AndersKTH,Numerisk Analys och Datalogi, NADA(Swepub:kth)u12s8cr8
(author)
-
KTHNumerisk Analys och Datalogi, NADA
(creator_code:org_t)
Related titles
-
In:ESANN'2006, s. 161-1662930307064
Internet link
Find in a library
-
ESANN'2006
(Search for host publication in LIBRIS)
To the university's database