Reading checks with multilayer graph transformer networks

Yann LeCun, Léon Bottou, Yoshua Bengio

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.
BibTeX
@inproceedings{lecun1997reading,
  author = {Yann LeCun and Léon Bottou and Yoshua Bengio},
  title = {{Reading checks with multilayer graph transformer networks}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {1997},
  doi = {10.1109/icassp.1997.599580},
}

Loading related content...

Figure