Skip navigation
Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.advisorVerma, Naveen-
dc.contributor.authorWharton, David-
dc.description.abstractThere are many trade-offs that arise when designing applications for embedded hardware, specifically algorithms for classification, operating on low-power embedded hardware with machine learning accelerators that necessitate good engineering decisions to be made. The trade-offs explored by this work are classification accuracy, energy consumption and mem- ory requirements. Three applications in the computer vision domain are the focus of this work.en_US
dc.format.extent68 pages*
dc.titleClassification Algorithms for Embedded Hardwareen_US
dc.typePrinceton University Senior Theses-
pu.departmentElectrical Engineeringen_US
Appears in Collections:Electrical Engineering, 1932-2020

Files in This Item:
File SizeFormat 
Wharton_David.pdf4.69 MBAdobe PDF    Request a copy

Items in Dataspace are protected by copyright, with all rights reserved, unless otherwise indicated.