A general-purpose dynamically reconfigurable SVM

Jonas Gomes Filho, Mario Raffo, Marius Strum, Wang Jiang Chau

Producción científica: Capítulo del libro/informe/acta de congresoContribución a la conferenciarevisión exhaustiva

7 Citas (Scopus)

Resumen

This paper presents an hardware implementation of the Sequential Minimal Optimization (SMO) for the Support Vector Machine (SVM) training phase. A general-purpose reconfigurable architecture, aimed to partial reconfiguration FPGAs, is developed, i.e., it supports different sizes of training sets, with wide-range number of samples and elements. The effects of fixed-point implementation are analyzed and data on area and frequency targeting the Xilinx Virtex-IV XC4VLX25 FPGA are provided. The architecture was able to perform the training in different learning benchmarks and the reconfigurable architecture was able to save 22.38% of FPGA's area.

Idioma originalInglés
Título de la publicación alojada6th Southern Programmable Logic Conference, SPL 2010 - Proceedings
Páginas107-112
Número de páginas6
DOI
EstadoPublicada - 2010
Publicado de forma externa
Evento6th Southern Programmable Logic Conference, SPL 2010 - Ipojuca, Brasil
Duración: 24 mar. 201026 mar. 2010

Serie de la publicación

Nombre6th Southern Programmable Logic Conference, SPL 2010 - Proceedings

Conferencia

Conferencia6th Southern Programmable Logic Conference, SPL 2010
País/TerritorioBrasil
CiudadIpojuca
Período24/03/1026/03/10

Huella

Profundice en los temas de investigación de 'A general-purpose dynamically reconfigurable SVM'. En conjunto forman una huella única.

Citar esto