Data processing: artificial intelligence – Plural processing systems
Patent
1997-03-11
2000-10-03
Hafiz, Tariq R.
Data processing: artificial intelligence
Plural processing systems
706 12, 706 14, G06F 1500
Patent
active
061286060
ABSTRACT:
A machine learning paradigm called Graph Transformer Networks 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 concept is described. The system uses convolutional neural network character recognizers, combined with global training techniques to provides record accuracy on business and personal checks.
REFERENCES:
patent: 4713778 (1987-12-01), Baker
patent: 4829450 (1989-05-01), Manthey
patent: 5067165 (1991-11-01), Nishida
patent: 5430744 (1995-07-01), Fettweis et al.
Yann Le Cun et al. "Word-Level Training of a Handritten Word Recognizer Based on Convolutional Neural Networks," Proceedings of the IAPR International Conference on Pattern Recognition, Oct. 1994, pp. 88-92.
S. Osowski et al., "Application of SFG in Learning Algorithms of Neural Networks," Proceedings of the International Workshop on Neural Networks for Identification, Control, Robotics, and Signal/Image Processing, Aug. 1996, pp. 75-83.
Yann Le Cun et al. Word-Level Training of a Handritten Word Recognizer Based on Convolutional Neutral Networks, Proceedings of the IAPR International Conference on Pattern Recognition, Oct. 1994, pp. 88-92.
Lou Zhensheng et al. The Parallel Model for Syntax Analysis with Uniform Graph Transformation Mechanism, Proceedings of the 3rd Pacific RIM International Conference on Artificial Intelligence, Aug. 15, 1994, pp. 649-657.
Bengio Yoshua
Bottou Leon
LeCun Yann Andre
AT&T Corporation
Hafiz Tariq R.
Rhodes Jason W.
LandOfFree
Module for constructing trainable modular network in which each does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Module for constructing trainable modular network in which each , we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Module for constructing trainable modular network in which each will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-204601