ALEXANDRIA, Va., Sept. 8 -- United States Patent no. 12,731,213, issued on Sept. 8, was assigned to Microsoft Technology Licensing LLC (Redmond, Wash.).

"Phased loss function training for super-resolution models" was invented by Sameer Avinash Nene (Redmond, Wash.), Matthew Lawrence Bronder (Bellevue, Wash.) and Michael George Boulton (Seattle).

According to the abstract* released by the U.S. Patent & Trademark Office: "Phased loss function training of machine learning models that are configured for performing super-resolution image processing includes training with two or more discrete phases that each apply different combinations of loss function training to the super-resolution models. In a first phase, for example, a first loss functi...