Abstract
An efficient neural network computing technique capable of synthesizing two sets of output signal data from a single input signal data set. The method and device of the invention involves a unique integration of autoassociative and heteroassociative neural network mappings, the autoassociative neural network mapping enabling a quality metric for assessing the generalization or prediction accuracy of the heteroassociative neural network mapping.
Document Type
Patent
Status
Issued
Issue Date
6-4-2020
Patent Number
US 6401082 B1 [6,401,082]
CPC Classification
G06N3/045
Application number
09/434549
Assignees
Government of the United States, as represented by the Secretary of the Air Force, Wright-Patterson AFB, OH (US)
Filing Date
11-8-1999
Recommended Citation
Kropas-Hughes, Claudia V.; Rogers, Steven K.; Oxley, Mark E.; and Kabrisky, Matthew, "Autoassociative-heteroassociative Neural Network" (2020). AFIT Patents. 63.
https://scholar.afit.edu/patents/63
Included in
Data Science Commons, Digital Communications and Networking Commons, Probability Commons, Signal Processing Commons
Comments
Kropas-Hughes, Claudia V., Steven K. Rogers, Mark E. Oxley, and Matthew Kabrisky. United States Patent 6401082 (B1), issued 4 June 2020. https://scholar.afit.edu/patents/63