Reading checks with multilayer graph transformer networks

Yann Le Cun, Leon Bottou, Yoshua Bengio

Research output: Contribution to journalConference articlepeer-review


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)
Pages (from-to)151-154
Number of pages4
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
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

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering


Dive into the research topics of 'Reading checks with multilayer graph transformer networks'. Together they form a unique fingerprint.

Cite this