dc.contributor.author | Tennebø, Frode | |
dc.contributor.author | Geitle, Marius | |
dc.date.accessioned | 2020-02-14T15:53:28Z | |
dc.date.available | 2020-02-14T15:53:28Z | |
dc.date.created | 2019-12-03T12:38:42Z | |
dc.date.issued | 2019-11-14 | |
dc.identifier.citation | NIK: Norsk Informatikkonferanse. 2019. | nb_NO |
dc.identifier.issn | 1892-0713 | |
dc.identifier.uri | http://hdl.handle.net/11250/2641832 | |
dc.description.abstract | Recently, there has been an increased interest in using artificial neural networks in the severely resource-constrained devices found in Internet-of-Things networks, in order to perform actions learned from the raw sensor data gathered by these devices. Unfortunately, training neural networks to achieve optimal prediction accuracy requires tuning multiple hyper-parameters, a process which has traditionally taken many times the computation time of a single training run of the neural network. In this paper, we empirically evaluate the Population Based Training algorithm, a method which simultaneously both trains and tunes a neural network, on datasets of similar size to what we might encounter in an IoT scenario. We determine that the population based training algorithm achieves prediction accuracy comparable to a traditional grid or random search on small datasets, and achieves state-of-the-art results for the Biodeg dataset. | nb_NO |
dc.language.iso | eng | nb_NO |
dc.publisher | Norsk informatikkonferanse NIK | nb_NO |
dc.relation.uri | https://ojs.bibsys.no/index.php/NIK/article/view/637 | |
dc.title | Evaluating Population Based Training on Small Datasets | nb_NO |
dc.type | Journal article | nb_NO |
dc.type | Peer reviewed | nb_NO |
dc.description.version | publishedVersion | nb_NO |
dc.subject.nsi | VDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550 | nb_NO |
dc.source.journal | NIK: Norsk Informatikkonferanse | nb_NO |
dc.identifier.cristin | 1756014 | |
cristin.unitcode | 224,55,0,0 | |
cristin.unitname | Avdeling for informasjonsteknologi | |
cristin.ispublished | true | |
cristin.fulltext | original | |
cristin.qualitycode | 1 | |