Patents by Inventor Frederick E. Daum

Frederick E. Daum has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 12682220
    Abstract: 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, using training particle flow, the particles resulting in optimized distributions for the parameters, determining a prediction distribution using the optimized distributions for the parameters and predictions from each of the NNs, and providing a marginalized distribution representative of the prediction distribution.
    Type: Grant
    Filed: October 25, 2021
    Date of Patent: July 14, 2026
    Assignee: Raytheon Company
    Inventors: Suzanne M. Baker, Andrew C. Allerdt, Michael R. Salpukas, Frederick E. Daum
  • Publication number: 20230129784
    Abstract: 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, using training particle flow, the particles resulting in optimized distributions for the parameters, determining a prediction distribution using the optimized distributions for the parameters and predictions from each of the NNs, and providing a marginalized distribution representative of the prediction distribution.
    Type: Application
    Filed: October 25, 2021
    Publication date: April 27, 2023
    Inventors: Suzanne M. Baker, Andrew C. Allerdt, Michael R. Salpukas, Frederick E. Daum