Please use this identifier to cite or link to this item: https://doi.org/10.1162/089976601300014493
DC FieldValue
dc.titleImprovements to Platt's SMO algorithm for SVM classifier design
dc.contributor.authorKeerthi, S.S.
dc.contributor.authorShevade, S.K.
dc.contributor.authorBhattacharyya, C.
dc.contributor.authorMurthy, K.R.K.
dc.date.accessioned2014-06-17T06:23:56Z
dc.date.available2014-06-17T06:23:56Z
dc.date.issued2001-03
dc.identifier.citationKeerthi, S.S., Shevade, S.K., Bhattacharyya, C., Murthy, K.R.K. (2001-03). Improvements to Platt's SMO algorithm for SVM classifier design. Neural Computation 13 (3) : 637-649. ScholarBank@NUS Repository. https://doi.org/10.1162/089976601300014493
dc.identifier.issn08997667
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/60498
dc.description.abstractThis article points out an important source of inefficiency in Platt's sequential minimal optimization (SMO) algorithm that is caused by the use of a single threshold value. Using clues from the KKT conditions for the dual problem, two threshold parameters are employed to derive modifications of SMO. These modified algorithms perform significantly faster than the original SMO on all benchmark data sets tried.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1162/089976601300014493
dc.sourceScopus
dc.typeArticle
dc.contributor.departmentMECHANICAL ENGINEERING
dc.description.doi10.1162/089976601300014493
dc.description.sourcetitleNeural Computation
dc.description.volume13
dc.description.issue3
dc.description.page637-649
dc.identifier.isiut000167362000008
Appears in Collections:Staff Publications

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

SCOPUSTM   
Citations

1,070
checked on Oct 11, 2019

WEB OF SCIENCETM
Citations

785
checked on Oct 11, 2019

Page view(s)

74
checked on Oct 13, 2019

Google ScholarTM

Check

Altmetric


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