Application of the ANNA neural network chip to high-speed character recognition

Eduard Sackinger, Bernhard E. Boser, Jane Bromley, Yann LeCun, Lawrence D. Jackel

Research output: Contribution to journalArticle

Abstract

A neural network with 136,000 connections for recognition of handwritten digits has been implemented using a mixed analog/digital neural network chip. The neural network chip is capable of processing 1000 characters/s. The recognition system has essentially the same rate (5%) as a simulation of the network with 32-b floating-point precision.

Original languageEnglish (US)
Pages (from-to)498-505
Number of pages8
JournalIEEE Transactions on Neural Networks
Volume3
Issue number3
DOIs
StatePublished - May 1992

Fingerprint

Character recognition
Character Recognition
High Speed
Chip
Neural Networks
Neural networks
Floating point
Digit
Analogue
Processing
Simulation

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Hardware and Architecture
  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Theoretical Computer Science

Cite this

Application of the ANNA neural network chip to high-speed character recognition. / Sackinger, Eduard; Boser, Bernhard E.; Bromley, Jane; LeCun, Yann; Jackel, Lawrence D.

In: IEEE Transactions on Neural Networks, Vol. 3, No. 3, 05.1992, p. 498-505.

Research output: Contribution to journalArticle

Sackinger, Eduard ; Boser, Bernhard E. ; Bromley, Jane ; LeCun, Yann ; Jackel, Lawrence D. / Application of the ANNA neural network chip to high-speed character recognition. In: IEEE Transactions on Neural Networks. 1992 ; Vol. 3, No. 3. pp. 498-505.
@article{341a49ceb4df4aaeb4073cb619cf7f5e,
title = "Application of the ANNA neural network chip to high-speed character recognition",
abstract = "A neural network with 136,000 connections for recognition of handwritten digits has been implemented using a mixed analog/digital neural network chip. The neural network chip is capable of processing 1000 characters/s. The recognition system has essentially the same rate (5{\%}) as a simulation of the network with 32-b floating-point precision.",
author = "Eduard Sackinger and Boser, {Bernhard E.} and Jane Bromley and Yann LeCun and Jackel, {Lawrence D.}",
year = "1992",
month = "5",
doi = "10.1109/72.129422",
language = "English (US)",
volume = "3",
pages = "498--505",
journal = "IEEE Transactions on Neural Networks and Learning Systems",
issn = "2162-237X",
publisher = "IEEE Computational Intelligence Society",
number = "3",

}

TY - JOUR

T1 - Application of the ANNA neural network chip to high-speed character recognition

AU - Sackinger, Eduard

AU - Boser, Bernhard E.

AU - Bromley, Jane

AU - LeCun, Yann

AU - Jackel, Lawrence D.

PY - 1992/5

Y1 - 1992/5

N2 - A neural network with 136,000 connections for recognition of handwritten digits has been implemented using a mixed analog/digital neural network chip. The neural network chip is capable of processing 1000 characters/s. The recognition system has essentially the same rate (5%) as a simulation of the network with 32-b floating-point precision.

AB - A neural network with 136,000 connections for recognition of handwritten digits has been implemented using a mixed analog/digital neural network chip. The neural network chip is capable of processing 1000 characters/s. The recognition system has essentially the same rate (5%) as a simulation of the network with 32-b floating-point precision.

UR - http://www.scopus.com/inward/record.url?scp=0026866736&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026866736&partnerID=8YFLogxK

U2 - 10.1109/72.129422

DO - 10.1109/72.129422

M3 - Article

AN - SCOPUS:0026866736

VL - 3

SP - 498

EP - 505

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

SN - 2162-237X

IS - 3

ER -