SVM-based Sketch Recognition: Which Hyperparameter Interval to Try?

Simple item page
dc.contributor.authorYesilbek, Kemal Tugrulen_US
dc.contributor.authorSen, Cansuen_US
dc.contributor.authorCakmak, Serikeen_US
dc.contributor.authorSezgin, T. Metinen_US
dc.contributor.editorErgun Aklemanen_US
dc.date.accessioned2015-06-22T07:06:53Z
dc.date.available2015-06-22T07:06:53Z
dc.date.issued2015en_US
dc.description.abstractHyperparameters are among the most crucial factors that affect the performance of machine learning algorithms. In general, there is no direct method for determining a set of satisfactory parameters, so hyperparameter search needs to be conducted each time a model is to be trained. In this work, we analyze how similar hyperparameters perform across various datasets from the sketch recognition domain. Results show that hyperparameter search space can be reduced to a subspace despite differences in characteristics of datasets.en_US
dc.description.sectionheadersRecognitionen_US
dc.description.seriesinformationSketch-Based Interfaces and Modelingen_US
dc.identifier.doi10.2312/exp.20151184en_US
dc.identifier.pages117-121en_US
dc.identifier.urihttps://doi.org/10.2312/exp.20151184en_US
dc.publisherThe Eurographics Associationen_US
dc.subjectI.5.0 [Pattern Recognition]en_US
dc.subjectGeneralen_US
dc.subjectH.5.2 [Information Interfaces and Presentation]en_US
dc.subjectUser Interfacesen_US
dc.subjectInput devices and strategiesen_US
dc.titleSVM-based Sketch Recognition: Which Hyperparameter Interval to Try?en_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
117-121.pdf
Size:
412.39 KB
Format:
Adobe Portable Document Format
Download
Collections
SBM15: Sketch Based Interfaces and Modeling 2015