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

dc.contributor.author Bihl, Trevor
dc.contributor.author Schoenbeck, Joe
dc.contributor.author Steeneck, Daniel
dc.contributor.author Jordan, Jeremy
dc.date.accessioned 2020-01-04T07:20:14Z
dc.date.available 2020-01-04T07:20:14Z
dc.date.issued 2020-01-07
dc.description.abstract Artificial 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.extent 10 pages
dc.identifier.doi 10.24251/HICSS.2020.118
dc.identifier.isbn 978-0-9981331-3-3
dc.identifier.uri http://hdl.handle.net/10125/63857
dc.language.iso eng
dc.relation.ispartof Proceedings of the 53rd Hawaii International Conference on System Sciences
dc.rights Attribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.uri https://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subject Big Data and Analytics: Pathways to Maturity
dc.subject hyperparameters
dc.subject machine learning
dc.subject professional practice
dc.subject repeatability
dc.title Easy and Efficient Hyperparameter Optimization to Address Some Artificial Intelligence “ilities”
dc.type Conference Paper
dc.type.dcmi Text
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
0094.pdf
Size:
752.85 KB
Format:
Adobe Portable Document Format
Description: