Reading checks with multilayer graph transformer networks

  • Yann Le Cun
  • Bottou L
  • Bengio Y
  • 80


    Mendeley users who have this article in their library.
  • 22


    Citations of this article.


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 millions of business and personal checks per month with record accuracy.

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document


  • Yann Le Cun

  • L. Bottou

  • Y. Bengio

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free