Predictive self-organizing neural network
Patent 5214715 Issued on May 25, 1993. Estimated Expiration Date: 
January 31, 2011. 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.
January 31, 2011. 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.Patent ReferencesParallel, multi-unit, adaptive, nonlinear pattern class separator and identifier Neural network apparatus and method for pattern recognition Pattern recognition apparatus using a neural network system Plural neural network system having a successive approximation learning method Patent #: 5095443 InventorsAssigneeApplicationNo. 648653 filed on 01/31/1991US Classes:382/157, Network learning techniques (e.g., back propagation)382/159, Trainable classifiers or pattern recognizers (e.g., adaline, perceptron)706/20, Classification or recognition706/25, Learning method706/27ArchitectureExaminersPrimary: Boudreau, Leo H.Assistant: Cammarata, Michael Attorney, Agent or FirmForeign Patent References
International ClassG06K 009/62AbstractAn A pattern recognition subsystem responds to an A feature representation input to select A-category-representation and predict a B-category-representation and its associated B feature representation input. During learning trials, a predicted B-category-representation is compared to that obtained through a B pattern recognition subsystem. With mismatch, a vigilance parameter of the A-pattern-recognition subsystem is increased to cause reset of the first-category-representation selection. Inputs to the pattern recognition subsystems may be preprocessed to complement code the inputs.Other References
| |
