Optical character recognition: A technology driver for neural networks

R. E. Howard; B. Boser; J. S. Denker; H. P. Graf; D. Henderson; W. Hubbard; L. D. Jackel; Y. Le Cun; H. S. Baird

Optical character recognition: A technology driver for neural networks

R. E. Howard, B. Boser, J. S. Denker, H. P. Graf, D. Henderson, W. Hubbard, L. D. Jackel, Y. Le Cun, H. S. Baird

Computer Science

Research output: Contribution to journal › Conference article › peer-review

Abstract

It is shown that a neural net can perform handwritten digit recognition with state-of-the-art accuracy. The solution required automatic learning and generalization from thousands of training examples and also required designing into the system considerable knowledge about the task--neither engineering nor learning from examples alone would have sufficed. The resulting network is well suited for implementation on workstations or PCs and can take advantage of digital signal processors (DSPs) or custom VLSI.

Original language	English (US)
Pages (from-to)	2433-2436
Number of pages	4
Journal	Proceedings - IEEE International Symposium on Circuits and Systems
Volume	3
State	Published - 1990
Event	1990 IEEE International Symposium on Circuits and Systems Part 3 (of 4) - New Orleans, LA, USA Duration: May 1 1990 → May 3 1990

ASJC Scopus subject areas

Electrical and Electronic Engineering

Cite this

@article{b9dac13662b8473c8b8beec9b29f8a99,

title = "Optical character recognition: A technology driver for neural networks",

abstract = "It is shown that a neural net can perform handwritten digit recognition with state-of-the-art accuracy. The solution required automatic learning and generalization from thousands of training examples and also required designing into the system considerable knowledge about the task--neither engineering nor learning from examples alone would have sufficed. The resulting network is well suited for implementation on workstations or PCs and can take advantage of digital signal processors (DSPs) or custom VLSI.",

author = "Howard, {R. E.} and B. Boser and Denker, {J. S.} and Graf, {H. P.} and D. Henderson and W. Hubbard and Jackel, {L. D.} and {Le Cun}, Y. and Baird, {H. S.}",

year = "1990",

language = "English (US)",

volume = "3",

pages = "2433--2436",

journal = "Proceedings - IEEE International Symposium on Circuits and Systems",

issn = "0271-4310",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "1990 IEEE International Symposium on Circuits and Systems Part 3 (of 4) ; Conference date: 01-05-1990 Through 03-05-1990",

}

TY - JOUR

T1 - Optical character recognition

T2 - 1990 IEEE International Symposium on Circuits and Systems Part 3 (of 4)

AU - Howard, R. E.

AU - Boser, B.

AU - Denker, J. S.

AU - Graf, H. P.

AU - Henderson, D.

AU - Hubbard, W.

AU - Jackel, L. D.

AU - Le Cun, Y.

AU - Baird, H. S.

PY - 1990

Y1 - 1990

N2 - It is shown that a neural net can perform handwritten digit recognition with state-of-the-art accuracy. The solution required automatic learning and generalization from thousands of training examples and also required designing into the system considerable knowledge about the task--neither engineering nor learning from examples alone would have sufficed. The resulting network is well suited for implementation on workstations or PCs and can take advantage of digital signal processors (DSPs) or custom VLSI.

AB - It is shown that a neural net can perform handwritten digit recognition with state-of-the-art accuracy. The solution required automatic learning and generalization from thousands of training examples and also required designing into the system considerable knowledge about the task--neither engineering nor learning from examples alone would have sufficed. The resulting network is well suited for implementation on workstations or PCs and can take advantage of digital signal processors (DSPs) or custom VLSI.

UR - http://www.scopus.com/inward/record.url?scp=0025596056&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025596056&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0025596056

SN - 0271-4310

VL - 3

SP - 2433

EP - 2436

JO - Proceedings - IEEE International Symposium on Circuits and Systems

JF - Proceedings - IEEE International Symposium on Circuits and Systems

Y2 - 1 May 1990 through 3 May 1990

ER -

Optical character recognition: A technology driver for neural networks

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this