A compact multi-chip-module implementation of a multi-precision neural network classifier

Amine Bermak, Dominique Martinez

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

2 Citations (Scopus)

Abstract

This paper describes a novel MCM digital implementation of a reconfigurable multi-precision neural network classifier. The design is based on a scalable systolic architecture with a user defined topology and arithmetic precision of the neural network. Indeed, the MCM integrates 64/32/16 neurons with a corresponding accuracy of 4/8/16-bits. A prototype has been designed and successfully tested in CMOS 0.7 μm technology.

Original languageEnglish
Title of host publicationISCAS 2001 - 2001 IEEE International Symposium on Circuits and Systems, Conference Proceedings
Pages249-252
Number of pages4
Volume3
DOIs
Publication statusPublished - 2001
Externally publishedYes
Event2001 IEEE International Symposium on Circuits and Systems, ISCAS 2001 - Sydney, NSW, Australia
Duration: 6 May 20019 May 2001

Other

Other2001 IEEE International Symposium on Circuits and Systems, ISCAS 2001
CountryAustralia
CitySydney, NSW
Period6/5/019/5/01

Fingerprint

Multicarrier modulation
Classifiers
Neural networks
Neurons
Topology

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials

Cite this

Bermak, A., & Martinez, D. (2001). A compact multi-chip-module implementation of a multi-precision neural network classifier. In ISCAS 2001 - 2001 IEEE International Symposium on Circuits and Systems, Conference Proceedings (Vol. 3, pp. 249-252). [921294] https://doi.org/10.1109/ISCAS.2001.921294

A compact multi-chip-module implementation of a multi-precision neural network classifier. / Bermak, Amine; Martinez, Dominique.

ISCAS 2001 - 2001 IEEE International Symposium on Circuits and Systems, Conference Proceedings. Vol. 3 2001. p. 249-252 921294.

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

Bermak, A & Martinez, D 2001, A compact multi-chip-module implementation of a multi-precision neural network classifier. in ISCAS 2001 - 2001 IEEE International Symposium on Circuits and Systems, Conference Proceedings. vol. 3, 921294, pp. 249-252, 2001 IEEE International Symposium on Circuits and Systems, ISCAS 2001, Sydney, NSW, Australia, 6/5/01. https://doi.org/10.1109/ISCAS.2001.921294
Bermak A, Martinez D. A compact multi-chip-module implementation of a multi-precision neural network classifier. In ISCAS 2001 - 2001 IEEE International Symposium on Circuits and Systems, Conference Proceedings. Vol. 3. 2001. p. 249-252. 921294 https://doi.org/10.1109/ISCAS.2001.921294
Bermak, Amine ; Martinez, Dominique. / A compact multi-chip-module implementation of a multi-precision neural network classifier. ISCAS 2001 - 2001 IEEE International Symposium on Circuits and Systems, Conference Proceedings. Vol. 3 2001. pp. 249-252
@inproceedings{1e6c3bf2fda240abac0138a96467bbab,
title = "A compact multi-chip-module implementation of a multi-precision neural network classifier",
abstract = "This paper describes a novel MCM digital implementation of a reconfigurable multi-precision neural network classifier. The design is based on a scalable systolic architecture with a user defined topology and arithmetic precision of the neural network. Indeed, the MCM integrates 64/32/16 neurons with a corresponding accuracy of 4/8/16-bits. A prototype has been designed and successfully tested in CMOS 0.7 μm technology.",
author = "Amine Bermak and Dominique Martinez",
year = "2001",
doi = "10.1109/ISCAS.2001.921294",
language = "English",
isbn = "0780366859",
volume = "3",
pages = "249--252",
booktitle = "ISCAS 2001 - 2001 IEEE International Symposium on Circuits and Systems, Conference Proceedings",

}

TY - GEN

T1 - A compact multi-chip-module implementation of a multi-precision neural network classifier

AU - Bermak, Amine

AU - Martinez, Dominique

PY - 2001

Y1 - 2001

N2 - This paper describes a novel MCM digital implementation of a reconfigurable multi-precision neural network classifier. The design is based on a scalable systolic architecture with a user defined topology and arithmetic precision of the neural network. Indeed, the MCM integrates 64/32/16 neurons with a corresponding accuracy of 4/8/16-bits. A prototype has been designed and successfully tested in CMOS 0.7 μm technology.

AB - This paper describes a novel MCM digital implementation of a reconfigurable multi-precision neural network classifier. The design is based on a scalable systolic architecture with a user defined topology and arithmetic precision of the neural network. Indeed, the MCM integrates 64/32/16 neurons with a corresponding accuracy of 4/8/16-bits. A prototype has been designed and successfully tested in CMOS 0.7 μm technology.

UR - http://www.scopus.com/inward/record.url?scp=0034998657&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034998657&partnerID=8YFLogxK

U2 - 10.1109/ISCAS.2001.921294

DO - 10.1109/ISCAS.2001.921294

M3 - Conference contribution

SN - 0780366859

SN - 9780780366855

VL - 3

SP - 249

EP - 252

BT - ISCAS 2001 - 2001 IEEE International Symposium on Circuits and Systems, Conference Proceedings

ER -