Granted Patent
Utility
US 6,018,728 · App. 08/797,497
Method and apparatus for training a neural network to learn hierarchical representations of objects and to detect and classify objects with uncertain training data
Inventors:
Clay Douglas Spence, John C. Pearson, Paul Sajda
Patented Case
View Patent ↗
Granted: Jan 25, 2000
Filed: Feb 7, 1997
Inventors
Clay Douglas Spence
John C. Pearson
Paul Sajda
Assignee (at issue)
Sarnoff Corporation
This patent predates the USPTO's electronic file wrapper — prosecution documents from this era exist only in the Patent Office's paper records. A certified copy of the file history can be ordered from the USPTO's paper archives.