ALEXANDRIA, Va., April 7 -- United States Patent no. 12,596,931, issued on April 7, was assigned to Amazon Technologies Inc. (Seattle).

"Selection of inputs for training machine-trained network" was invented by Steven L. Teig (Menlo Park, Calif.), Eric A. Sather (Palo Alto, Calif.), Andrew F. Siegel (Shoreline, Wash.) and Evgeny Sorkin (Vancouver, Canada).

According to the abstract* released by the U.S. Patent & Trademark Office: "Some embodiments provide a method for training a machine-trained network that includes multiple parameters. The method propagates a batch of input training items through the network to generate output values and compute values of a loss function for each of the input training items. The method uses the computed ...