The Community for Technology Leaders
Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (1997)
Puerto Rico
June 17, 1997 to June 19, 1997
ISSN: 1063-6919
ISBN: 0-8186-7822-4
pp: 489
Leon Bottou , AT&T Labs
Yoshua Bengio , AT&T Labs
Yann Le Cun , AT&T Labs
ABSTRACT
We propose a new machine learning paradigm called Graph Transformer Networks that extends the applicability of gradient-based learning algorithms to systems composed of modules that take graphs as inputs and produce graphs as output. Training is performed by computing gradients of a global objective function with respect to all the parameters in the system using a kind of back-propagation procedure.A complete check reading system based on these concepts is described. The system uses convolutional neural network character recognizers, combined with global training techniques to provide record accuracy on business and personal checks. It is presently deployed commercially and reads million of checks per month.
INDEX TERMS
Learning Algorithm, Graph Transformers
CITATION

Y. L. Cun, Y. Bengio and L. Bottou, "Global Training of Document Processing Systems Using Graph Transformer Networks," Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR), Puerto Rico, 1997, pp. 489.
doi:10.1109/CVPR.1997.609370
90 ms
(Ver 3.3 (11022016))