Show simple item record

dc.contributor.authorJönsson, Danielen_US
dc.contributor.authorEilertsen, Gabrielen_US
dc.contributor.authorShi, Hezien_US
dc.contributor.authorZheng, Jianminen_US
dc.contributor.authorYnnerman, Andersen_US
dc.contributor.authorUnger, Jonasen_US
dc.contributor.editorArchambault, Daniel and Nabney, Ian and Peltonen, Jaakkoen_US
dc.date.accessioned2020-05-24T13:27:43Z
dc.date.available2020-05-24T13:27:43Z
dc.date.issued2020
dc.identifier.isbn978-3-03868-113-7
dc.identifier.urihttps://doi.org/10.2312/mlvis.20201101
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/mlvis20201101
dc.description.abstractWe present an analysis of the impact of hyper-parameters for an ensemble of neural networks using tailored visualization techniques to understand the complicated relationship between hyper-parameters and model performance. The high-dimensional error surface spanned by the wide range of hyper-parameters used to specify and optimize neural networks is difficult to characterize - it is non-convex and discontinuous, and there could be complex local dependencies between hyper-parameters. To explore these dependencies, we make use of a large number of sampled relations between hyper-parameters and end performance, retrieved from thousands of individually trained convolutional neural network classifiers. We use a structured selection of visualization techniques to analyze the impact of different combinations of hyper-parameters. The results reveal how complicated dependencies between hyper-parameters influence the end performance, demonstrating how the complete picture painted by considering a large number of trainings simultaneously can aid in understanding the impact of hyper-parameter combinations.en_US
dc.publisherThe Eurographics Associationen_US
dc.subjectComputing methodologies
dc.subjectNeural networks
dc.subjectHuman
dc.subjectcentered computing
dc.subjectVisual analytics
dc.titleVisual Analysis of the Impact of Neural Network Hyper-Parametersen_US
dc.description.seriesinformationMachine Learning Methods in Visualisation for Big Data
dc.description.sectionheadersPapers
dc.identifier.doi10.2312/mlvis.20201101
dc.identifier.pages13-17


Files in this item

Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record