Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/43188
DC FieldValue
dc.titleHandwritten digit recognition with a novel vision model that extracts linearly separable features
dc.contributor.authorTeow, Loo-Nin
dc.contributor.authorLoe, Kia-Fock
dc.date.accessioned2013-07-23T09:27:23Z
dc.date.available2013-07-23T09:27:23Z
dc.date.issued2000
dc.identifier.citationTeow, Loo-Nin,Loe, Kia-Fock (2000). Handwritten digit recognition with a novel vision model that extracts linearly separable features. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2 : 76-81. ScholarBank@NUS Repository.
dc.identifier.issn10636919
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/43188
dc.description.abstractWe use well-established results in biological vision to construct a novel vision model for handwritten digit recognition. We show empirically that the features extracted by our model are linearly separable over a large training set (MNIST). Using only a linear classifier on these features, our model is relatively simple yet outperforms other models on the same data set.
dc.sourceScopus
dc.typeConference Paper
dc.contributor.departmentCOMPUTER SCIENCE
dc.contributor.departmentINSTITUTE OF SYSTEMS SCIENCE
dc.description.sourcetitleProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
dc.description.volume2
dc.description.page76-81
dc.description.codenPIVRE
dc.identifier.isiutNOT_IN_WOS
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

Page view(s)

91
checked on Sep 9, 2019

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.