Show simple item record

dc.contributor.authorCodreanu, Valeriu
dc.contributor.authorDröge, Bob
dc.contributor.authorWilliams, David
dc.contributor.authorYasar, Burhan
dc.contributor.authorYang, Po
dc.contributor.authorLiu, Baoquan
dc.contributor.authorDong, Feng
dc.contributor.authorSurinta, Olarik
dc.contributor.authorSchomaker, Lambert R.B.
dc.contributor.authorRoerdink, Jos B.T.M.
dc.contributor.authorWiering, Marco A.
dc.date.accessioned2020-08-17T08:53:37Z
dc.date.available2020-08-17T08:53:37Z
dc.date.issued2014-10-09
dc.identifier.citationCodreanu V., Dröge B., Williams D., Yasar B., Yang P., Liu B., Dong F., Surinta O., Schomaker L., Roerdink J., Wiering M. (2016) 'Evaluating automatically parallelized versions of the support vector machine', Concurrency and Computation: Practice and Experience, 28 (7), pp.2274-2294.en_US
dc.identifier.issn1532-0626
dc.identifier.doi10.1002/cpe.3413
dc.identifier.urihttp://hdl.handle.net/10547/624418
dc.description.abstractThe support vector machine (SVM) is a supervised learning algorithm used for recognizing patterns in data. It is a very popular technique in machine learning and has been successfully used in applications such as image classification, protein classification, and handwriting recognition. However, the computational complexity of the kernelized version of the algorithm grows quadratically with the number of training examples. To tackle this high computational complexity, we have developed a directive-based approach that converts a gradient-ascent based training algorithm for the CPU to an efficient graphics processing unit (GPU) implementation. We compare our GPU-based SVM training algorithm to the standard LibSVM CPU implementation, a highly optimized GPU-LibSVM implementation, as well as to a directive-based OpenACC implementation. The results on different handwritten digit classification datasets demonstrate an important speed-up for the current approach when compared to the CPU and OpenACC versions. Furthermore, our solution is almost as fast and sometimes even faster than the highly optimized CUBLAS-based GPU-LibSVM implementation, without sacrificing the algorithm's accuracy.en_US
dc.language.isoenen_US
dc.publisherJohn Wiley and Sons Ltden_US
dc.relation.urlhttps://onlinelibrary.wiley.com/doi/abs/10.1002/cpe.3413en_US
dc.rightsYellow - can archive pre-print (ie pre-refereeing)
dc.subjecthandwritten digit recognitionen_US
dc.subjectsupport vector machineen_US
dc.subjectautomatic parallelizationen_US
dc.subjectautomatic parallelizationen_US
dc.subjectGPUen_US
dc.titleEvaluating automatically parallelized versions of the support vector machineen_US
dc.typeArticleen_US
dc.identifier.journalConcurrency and Computation: Practice and Experienceen_US
dc.date.updated2020-08-17T08:48:19Z
dc.description.note


This item appears in the following Collection(s)

Show simple item record