Module for constructing trainable modular network in which each module inputs and outputs data structured as a graph

Patent 6128606 Issued on October 3, 2000. Estimated Expiration Date:

March 11, 2017. Estimated Expiration Date is calculated based on simple USPTO term provisions. It does not account for terminal disclaimers, term adjustments, failure to pay maintenance fees, or other factors which might affect the term of a patent.

Abstract Claims Description Full Text

Patent References

Speech recognition method
Patent #: 4713778
Issued on: 12/15/1987
Inventor: Baker

Reasoning machine
Patent #: 4829450
Issued on: 05/09/1989
Inventor: Manthey

Character recognition method
Patent #: 5067165
Issued on: 11/19/1991
Inventor: Nishida, ;, , , --> Nishida

Method and means for detecting partial response waveforms using a modified dynamic programming heuristic Patent #: 5430744
Issued on: 07/04/1995
Inventor: Fettweis, et al.

Inventors

Application

No. 815504 filed on 03/11/1997

US Classes:

706/10, PLURAL PROCESSING SYSTEMS706/12, MACHINE LEARNING706/14ADAPTIVE SYSTEM

Examiners

Primary: Hafiz, Tariq R.
Assistant: Rhodes, Jason W.

Attorney, Agent or Firm

Kenyon & Kenyon

International Class

G06F 015/00

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.

Other References

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. 649-65