Reading checks with multilayer graph transformer networks

Yann LeCun, Leon Bottou, Yoshua Bengio

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

Abstract

We propose a new machine learning paradigm called Multilayer Graph Transformer Network that extends the applicability of gradient-based learning algorithms to systems composed of modules that take graphs as input and produce graphs as output. A complete check reading system based on this concept is described. The system combines convolutional neural network character recognizers with graph-based stochastic models trained cooperatively at the document level. It is deployed commercially and reads million of business and personal checks per month with record accuracy.

Original languageEnglish (US)
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Editors Anon
PublisherIEEE
Pages151-154
Number of pages4
Volume1
StatePublished - 1997
EventProceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP. Part 1 (of 5) - Munich, Ger
Duration: Apr 21 1997Apr 24 1997

Other

OtherProceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP. Part 1 (of 5)
CityMunich, Ger
Period4/21/974/24/97

Fingerprint

Stochastic models
transformers
Learning algorithms
Learning systems
Multilayers
Neural networks
machine learning
learning
Industry
modules
gradients
output

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Acoustics and Ultrasonics

Cite this

LeCun, Y., Bottou, L., & Bengio, Y. (1997). Reading checks with multilayer graph transformer networks. In Anon (Ed.), ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (Vol. 1, pp. 151-154). IEEE.

Reading checks with multilayer graph transformer networks. / LeCun, Yann; Bottou, Leon; Bengio, Yoshua.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. ed. / Anon. Vol. 1 IEEE, 1997. p. 151-154.

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

LeCun, Y, Bottou, L & Bengio, Y 1997, Reading checks with multilayer graph transformer networks. in Anon (ed.), ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. vol. 1, IEEE, pp. 151-154, Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP. Part 1 (of 5), Munich, Ger, 4/21/97.
LeCun Y, Bottou L, Bengio Y. Reading checks with multilayer graph transformer networks. In Anon, editor, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 1. IEEE. 1997. p. 151-154
LeCun, Yann ; Bottou, Leon ; Bengio, Yoshua. / Reading checks with multilayer graph transformer networks. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. editor / Anon. Vol. 1 IEEE, 1997. pp. 151-154
@inproceedings{1bd41fc0120c48468fb1df5a96894e1f,
title = "Reading checks with multilayer graph transformer networks",
abstract = "We propose a new machine learning paradigm called Multilayer Graph Transformer Network that extends the applicability of gradient-based learning algorithms to systems composed of modules that take graphs as input and produce graphs as output. A complete check reading system based on this concept is described. The system combines convolutional neural network character recognizers with graph-based stochastic models trained cooperatively at the document level. It is deployed commercially and reads million of business and personal checks per month with record accuracy.",
author = "Yann LeCun and Leon Bottou and Yoshua Bengio",
year = "1997",
language = "English (US)",
volume = "1",
pages = "151--154",
editor = "Anon",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - Reading checks with multilayer graph transformer networks

AU - LeCun, Yann

AU - Bottou, Leon

AU - Bengio, Yoshua

PY - 1997

Y1 - 1997

N2 - We propose a new machine learning paradigm called Multilayer Graph Transformer Network that extends the applicability of gradient-based learning algorithms to systems composed of modules that take graphs as input and produce graphs as output. A complete check reading system based on this concept is described. The system combines convolutional neural network character recognizers with graph-based stochastic models trained cooperatively at the document level. It is deployed commercially and reads million of business and personal checks per month with record accuracy.

AB - We propose a new machine learning paradigm called Multilayer Graph Transformer Network that extends the applicability of gradient-based learning algorithms to systems composed of modules that take graphs as input and produce graphs as output. A complete check reading system based on this concept is described. The system combines convolutional neural network character recognizers with graph-based stochastic models trained cooperatively at the document level. It is deployed commercially and reads million of business and personal checks per month with record accuracy.

UR - http://www.scopus.com/inward/record.url?scp=0030677452&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030677452&partnerID=8YFLogxK

M3 - Conference contribution

VL - 1

SP - 151

EP - 154

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

A2 - Anon, null

PB - IEEE

ER -