US Patent Issued to NVIDIA on Oct. 20 for "Training one or more neural networks using synthetic data" (California Inventors)

ALEXANDRIA, Va., Oct. 21 -- United States Patent no. 12,770,209, issued on Oct. 20, was assigned to NVIDIA Corp. (Santa Clara, Calif.).

"Training one or more neural networks using synthetic data" was invented by Robert Pottorff (Santa Clara, Calif.), Shiqiu Liu (Santa Clara, Calif.), Andrew Tao (Los Altos, Calif.) and Bryan Catanzaro (Los Altos Hills, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Apparatuses, systems, and techniques are presented to train one or more neural networks. In at least one embodiment, one or more neural networks are trained based, at least in part, on two or more versions of an image, wherein each of the two or more versions of the image are to be synthetically generated in...