Optimized Cellular Neural Network Universal Machine emulation on FPGA

Giovanni Egidio Pazienza; Jordi Bellana-Camañes; Jordi Riera-Baburés; Xavier Vilasís-Cardona; Marco Antonio Moreno-Armendáriz; Marco Balsi

doi:10.1109/ECCTD.2007.4529721

Optimized Cellular Neural Network Universal Machine emulation on FPGA

Giovanni Egidio Pazienza, Jordi Bellana-Camañes, Jordi Riera-Baburés, Xavier Vilasís-Cardona, Marco Antonio Moreno-Armendáriz, Marco Balsi

Centro de Investigación en Computación (CIC)

Producción científica: Contribución a una conferencia › Artículo

Resumen

An FPGA architecture to emulate a single-layer Cellular Neural Network - Universal Machine (CNN-UM) is proposed. It is based on a fast realization of the CNN convolution operation on the parallel hardware of the FPGA. The setup is capable of performing a CNN iteration over a 30×30 pixel image in less than 30 μs. Moreover, this platform has been used to realize the visual system of an autonomous mobile robot. © 2007 IEEE.

Idioma original	Inglés estadounidense
Páginas	815-818
Número de páginas	733
DOI	https://doi.org/10.1109/ECCTD.2007.4529721
Estado	Publicada - 25 ago. 2008
Evento	European Conference on Circuit Theory and Design 2007, ECCTD 2007 - Duración: 25 ago. 2008 → …

Conferencia

Conferencia	European Conference on Circuit Theory and Design 2007, ECCTD 2007
Período	25/08/08 → …

Acceder al documento

10.1109/ECCTD.2007.4529721

Otros archivos y enlaces

Citar esto

@conference{99a6b019bf164a76bea79d53c864211d,

title = "Optimized Cellular Neural Network Universal Machine emulation on FPGA",

abstract = "An FPGA architecture to emulate a single-layer Cellular Neural Network - Universal Machine (CNN-UM) is proposed. It is based on a fast realization of the CNN convolution operation on the parallel hardware of the FPGA. The setup is capable of performing a CNN iteration over a 30×30 pixel image in less than 30 μs. Moreover, this platform has been used to realize the visual system of an autonomous mobile robot. {\textcopyright} 2007 IEEE.",

author = "Pazienza, {Giovanni Egidio} and Jordi Bellana-Cama{\~n}es and Jordi Riera-Babur{\'e}s and Xavier Vilas{\'i}s-Cardona and Moreno-Armend{\'a}riz, {Marco Antonio} and Marco Balsi",

year = "2008",

month = aug,

day = "25",

doi = "10.1109/ECCTD.2007.4529721",

language = "American English",

pages = "815--818",

note = "European Conference on Circuit Theory and Design 2007, ECCTD 2007 ; Conference date: 25-08-2008",

}

TY - CONF

T1 - Optimized Cellular Neural Network Universal Machine emulation on FPGA

AU - Pazienza, Giovanni Egidio

AU - Bellana-Camañes, Jordi

AU - Riera-Baburés, Jordi

AU - Vilasís-Cardona, Xavier

AU - Moreno-Armendáriz, Marco Antonio

AU - Balsi, Marco

PY - 2008/8/25

Y1 - 2008/8/25

N2 - An FPGA architecture to emulate a single-layer Cellular Neural Network - Universal Machine (CNN-UM) is proposed. It is based on a fast realization of the CNN convolution operation on the parallel hardware of the FPGA. The setup is capable of performing a CNN iteration over a 30×30 pixel image in less than 30 μs. Moreover, this platform has been used to realize the visual system of an autonomous mobile robot. © 2007 IEEE.

AB - An FPGA architecture to emulate a single-layer Cellular Neural Network - Universal Machine (CNN-UM) is proposed. It is based on a fast realization of the CNN convolution operation on the parallel hardware of the FPGA. The setup is capable of performing a CNN iteration over a 30×30 pixel image in less than 30 μs. Moreover, this platform has been used to realize the visual system of an autonomous mobile robot. © 2007 IEEE.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=49749097134&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=49749097134&origin=inward

U2 - 10.1109/ECCTD.2007.4529721

DO - 10.1109/ECCTD.2007.4529721

M3 - Paper

SP - 815

EP - 818

T2 - European Conference on Circuit Theory and Design 2007, ECCTD 2007

Y2 - 25 August 2008

ER -

Optimized Cellular Neural Network Universal Machine emulation on FPGA

Resumen

Conferencia

Acceder al documento

Otros archivos y enlaces

Huella

Citar esto