Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (1997)
June 17, 1997 to June 19, 1997
Leon Bottou , AT&T Labs
Yoshua Bengio , AT&T Labs
Yann Le Cun , AT&T Labs
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.
Learning Algorithm, Graph Transformers
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.