US Patent Issued to Raytheon on July 14 for "Particle flow training of Bayesian neural network" (Massachusetts, Rhode Island Inventors)

ALEXANDRIA, Va., July 14 -- United States Patent no. 12,682,220, issued on July 14, was assigned to Raytheon Co. (Arlington, Va.).

"Particle flow training of Bayesian neural network" was invented by Suzanne M. Baker (Lincoln, Mass.), Andrew C. Allerdt (Tiverton, R.I.), Michael R. Salpukas (Lexington, Mass.) and Frederick E. Daum (Carlisle, Mass.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Discussed herein are devices, systems, and methods for training and operating a Bayesian neural network (BNN). A method can include initializing particles that each individually represent pointwise values of respective NN parameters of NNs that collectively represent a distribution of parameters of the BNN, optimizing, u...