Easy and Efficient Hyperparameter Optimization to Address Some Artificial Intelligence “ilities”

Simple item page
dc.contributor.authorBihl, Trevor
dc.contributor.authorSchoenbeck, Joe
dc.contributor.authorSteeneck, Daniel
dc.contributor.authorJordan, Jeremy
dc.date.accessioned2020-01-04T07:20:14Z
dc.date.available2020-01-04T07:20:14Z
dc.date.issued2020-01-07
dc.description.abstractArtificial Intelligence (AI), has many benefits, including the ability to find complex patterns, automation, and meaning making. Through these benefits, AI has revolutionized image processing among numerous other disciplines. AI further has the potential to revolutionize other domains; however, this will not happen until we can address the “ilities”: repeatability, explain-ability, reliability, use-ability, trust-ability, etc. Notably, many problems with the “ilities” are due to the artistic nature of AI algorithm development, especially hyperparameter determination. AI algorithms are often crafted products with the hyperparameters learned experientially. As such, when applying the same algorithm to new problems, the algorithm may not perform due to inappropriate settings. This research aims to provide a straightforward and reliable approach to automatically determining suitable hyperparameter settings when given an AI algorithm. Results, show reasonable performance is possible and end-to-end examples are given for three deep learning algorithms and three different data problems.
dc.format.extent10 pages
dc.identifier.doi10.24251/HICSS.2020.118
dc.identifier.isbn978-0-9981331-3-3
dc.identifier.urihttp://hdl.handle.net/10125/63857
dc.language.isoeng
dc.relation.ispartofProceedings of the 53rd Hawaii International Conference on System Sciences
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectBig Data and Analytics: Pathways to Maturity
dc.subjecthyperparameters
dc.subjectmachine learning
dc.subjectprofessional practice
dc.subjectrepeatability
dc.titleEasy and Efficient Hyperparameter Optimization to Address Some Artificial Intelligence “ilities”
dc.typeConference Paper
dc.type.dcmiText

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
0094.pdf
Size:
752.85 KB
Format:
Adobe Portable Document Format
Download

Collections

Big Data and Analytics: Pathways to Maturity