Dataflow Design for Optimal Incremental SVM Training

File Description SizeFormat 
fpt16ss.pdfAccepted version155.35 kBAdobe PDFView/Open
Title: Dataflow Design for Optimal Incremental SVM Training
Authors: Shao, S
Mencer, O
Luk, W
Item Type: Conference Paper
Abstract: This paper proposes a new parallel architecture for incremental training of a Support Vector Machine (SVM), which produces an optimal solution based on manipulating the Karush-Kuhn-Tucker (KKT) conditions. Compared to batch training methods, our approach avoids re-training from scratch when training dataset changes. The proposed architecture is the first to adopt an efficient dataflow organisation. The main novelty is a parametric description of the parallel dataflow architecture, which deploys customisable arithmetic units for dense linear algebraic operations involved in updating the KKT conditions. The proposed architecture targets on-line SVM training applications. Experimental evaluation with real world financial data shows that our architecture implemented on Stratix-V FPGA achieved significant speedup against LIBSVM on Core i7-4770 CPU.
Editors: Song, YC
Wang, S
Nelson, B
Li, J
Peng, Y
Issue Date: 18-May-2018
Date of Acceptance: 7-Dec-2016
Publisher: IEEE
Start Page: 197
End Page: 200
Journal / Book Title: Field-Programmable Technology (FPT), 2016 International Conference on
Copyright Statement: © 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Sponsor/Funder: Engineering & Physical Science Research Council (E
Commission of the European Communities
Engineering & Physical Science Research Council (E
Funder's Grant Number: PO 1553380
516075101 (EP/N031768/1)
Conference Name: 15th International Conference on Field-Programmable Technology (FPT)
Keywords: Science & Technology
Computer Science, Theory & Methods
Engineering, Electrical & Electronic
Computer Science
Publication Status: Published
Start Date: 2016-12-07
Finish Date: 2016-12-09
Conference Place: Xian, China
Appears in Collections:Faculty of Engineering

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

Creative Commons