CORDIC algorithms for SVM FPGA implementation

Jesús Gimeno Sarciada; Horacio Lamel Rivera; Matías Jiménez

doi:10.1117/12.850781

12 April 2010 CORDIC algorithms for SVM FPGA implementation

Jesús Gimeno Sarciada, Horacio Lamel Rivera, Matías Jiménez

Proceedings Volume 7703, Independent Component Analyses, Wavelets, Neural Networks, Biosystems, and Nanoengineering VIII; 77030G (2010) https://doi.org/10.1117/12.850781
Event: SPIE Defense, Security, and Sensing, 2010, Orlando, Florida, United States

Abstract

Support Vector Machines are currently one of the best classification algorithms used in a wide number of applications. The ability to extract a classification function from a limited number of learning examples keeping in the structural risk low has demonstrated to be a clear alternative to other neural networks. However, the calculations involved in computing the kernel and the repetition of the process for all support vectors in the classification problem are certainly intensive, requiring time or power consumption in order to function correctly. This problem could be a drawback in certain applications with limited resources or time. Therefore simple algorithms circumventing this problem are needed. In this paper we analyze an FPGA implementation of a SVM which uses a CORDIC algorithm for simplifying the calculation of as specific kernel greatly reducing the time and hardware requirements needed for the classification, allowing for powerful in-field portable applications. The algorithm is and its calculation capabilities are shown. The full SVM classifier using this algorithm is implemented in an FPGA and its in-field use assessed for high speed low power classification.

Citation Download Citation

Jesús Gimeno Sarciada, Horacio Lamel Rivera, and Matías Jiménez "CORDIC algorithms for SVM FPGA implementation", Proc. SPIE 7703, Independent Component Analyses, Wavelets, Neural Networks, Biosystems, and Nanoengineering VIII, 77030G (12 April 2010); https://doi.org/10.1117/12.850781

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available