Hardware accelerated convolutional neural networks for synthetic vision systems

Clément Farabet, Berin Martini, Polina Akselrod, Selçuk Talay, Yann LeCun, Eugenio Culurciello

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper we present a scalable hardware architecture to implement large-scale convolutional neural networks and state-of-the-art multi-layered artificial vision systems. This system is fully digital and is a modular vision engine with the goal of performing real-time detection, recognition and segmentation of mega-pixel images. We present a performance comparison between a software, FPGA and ASIC implementation that shows a speed up in custom hardware implementations.

Original languageEnglish (US)
Title of host publicationISCAS 2010 - 2010 IEEE International Symposium on Circuits and Systems: Nano-Bio Circuit Fabrics and Systems
Pages257-260
Number of pages4
DOIs
StatePublished - 2010
Event2010 IEEE International Symposium on Circuits and Systems: Nano-Bio Circuit Fabrics and Systems, ISCAS 2010 - Paris, France
Duration: May 30 2010Jun 2 2010

Other

Other2010 IEEE International Symposium on Circuits and Systems: Nano-Bio Circuit Fabrics and Systems, ISCAS 2010
CountryFrance
CityParis
Period5/30/106/2/10

Fingerprint

Neural networks
Hardware
Application specific integrated circuits
Computer vision
Field programmable gate arrays (FPGA)
Pixels
Engines

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Farabet, C., Martini, B., Akselrod, P., Talay, S., LeCun, Y., & Culurciello, E. (2010). Hardware accelerated convolutional neural networks for synthetic vision systems. In ISCAS 2010 - 2010 IEEE International Symposium on Circuits and Systems: Nano-Bio Circuit Fabrics and Systems (pp. 257-260). [5537908] https://doi.org/10.1109/ISCAS.2010.5537908

Hardware accelerated convolutional neural networks for synthetic vision systems. / Farabet, Clément; Martini, Berin; Akselrod, Polina; Talay, Selçuk; LeCun, Yann; Culurciello, Eugenio.

ISCAS 2010 - 2010 IEEE International Symposium on Circuits and Systems: Nano-Bio Circuit Fabrics and Systems. 2010. p. 257-260 5537908.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Farabet, C, Martini, B, Akselrod, P, Talay, S, LeCun, Y & Culurciello, E 2010, Hardware accelerated convolutional neural networks for synthetic vision systems. in ISCAS 2010 - 2010 IEEE International Symposium on Circuits and Systems: Nano-Bio Circuit Fabrics and Systems., 5537908, pp. 257-260, 2010 IEEE International Symposium on Circuits and Systems: Nano-Bio Circuit Fabrics and Systems, ISCAS 2010, Paris, France, 5/30/10. https://doi.org/10.1109/ISCAS.2010.5537908
Farabet C, Martini B, Akselrod P, Talay S, LeCun Y, Culurciello E. Hardware accelerated convolutional neural networks for synthetic vision systems. In ISCAS 2010 - 2010 IEEE International Symposium on Circuits and Systems: Nano-Bio Circuit Fabrics and Systems. 2010. p. 257-260. 5537908 https://doi.org/10.1109/ISCAS.2010.5537908
Farabet, Clément ; Martini, Berin ; Akselrod, Polina ; Talay, Selçuk ; LeCun, Yann ; Culurciello, Eugenio. / Hardware accelerated convolutional neural networks for synthetic vision systems. ISCAS 2010 - 2010 IEEE International Symposium on Circuits and Systems: Nano-Bio Circuit Fabrics and Systems. 2010. pp. 257-260
@inproceedings{49d7bdb87f754b4191362a0c982f0e4a,
title = "Hardware accelerated convolutional neural networks for synthetic vision systems",
abstract = "In this paper we present a scalable hardware architecture to implement large-scale convolutional neural networks and state-of-the-art multi-layered artificial vision systems. This system is fully digital and is a modular vision engine with the goal of performing real-time detection, recognition and segmentation of mega-pixel images. We present a performance comparison between a software, FPGA and ASIC implementation that shows a speed up in custom hardware implementations.",
author = "Cl{\'e}ment Farabet and Berin Martini and Polina Akselrod and Sel{\cc}uk Talay and Yann LeCun and Eugenio Culurciello",
year = "2010",
doi = "10.1109/ISCAS.2010.5537908",
language = "English (US)",
isbn = "9781424453085",
pages = "257--260",
booktitle = "ISCAS 2010 - 2010 IEEE International Symposium on Circuits and Systems: Nano-Bio Circuit Fabrics and Systems",

}

TY - GEN

T1 - Hardware accelerated convolutional neural networks for synthetic vision systems

AU - Farabet, Clément

AU - Martini, Berin

AU - Akselrod, Polina

AU - Talay, Selçuk

AU - LeCun, Yann

AU - Culurciello, Eugenio

PY - 2010

Y1 - 2010

N2 - In this paper we present a scalable hardware architecture to implement large-scale convolutional neural networks and state-of-the-art multi-layered artificial vision systems. This system is fully digital and is a modular vision engine with the goal of performing real-time detection, recognition and segmentation of mega-pixel images. We present a performance comparison between a software, FPGA and ASIC implementation that shows a speed up in custom hardware implementations.

AB - In this paper we present a scalable hardware architecture to implement large-scale convolutional neural networks and state-of-the-art multi-layered artificial vision systems. This system is fully digital and is a modular vision engine with the goal of performing real-time detection, recognition and segmentation of mega-pixel images. We present a performance comparison between a software, FPGA and ASIC implementation that shows a speed up in custom hardware implementations.

UR - http://www.scopus.com/inward/record.url?scp=77956000290&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956000290&partnerID=8YFLogxK

U2 - 10.1109/ISCAS.2010.5537908

DO - 10.1109/ISCAS.2010.5537908

M3 - Conference contribution

AN - SCOPUS:77956000290

SN - 9781424453085

SP - 257

EP - 260

BT - ISCAS 2010 - 2010 IEEE International Symposium on Circuits and Systems: Nano-Bio Circuit Fabrics and Systems

ER -