US Patent Issued to Rockwell Collins on Dec. 9 for "System and method for determining incoming observation to be out-of-distribution (OOD) sample during neural network (NN) inference" (Georgia, Connecticut Inventors)

ALEXANDRIA, Va., Dec. 9 -- United States Patent no. 12,494,052, issued on Dec. 9, was assigned to Rockwell Collins Inc. (Cedar Rapids, Iowa).

"System and method for determining incoming observation to be out-of-distribution (OOD) sample during neural network (NN) inference" was invented by Sudeepta Mondal (Bristol, Conn.) and Ganesh Sundaramoorthi (Duluth, Ga.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A system may include at least one processor configured to: obtain a trained neural network (NN); obtain or calculate at least one average feature information associated with the trained NN, each of the at least one average feature information including a given average feature information summarizing in-cla...