US Patent Issued to DeepMind Technologies on May 20 for "Training spectral inference neural networks using bilevel optimization" (British, American Inventors)

ALEXANDRIA, Va., June 16 -- United States Patent no. 12,307,376, issued on May 20, was assigned to DeepMind Technologies Ltd. (London).

"Training spectral inference neural networks using bilevel optimization" was invented by David Benjamin Pfau (London), Stig Petersen (Royston, Great Britain), Ashish Agarwal (Sunnyvale, Calif.), David Barrett (London) and Kimberly Stachenfeld (London).

According to the abstract* released by the U.S. Patent & Trademark Office: "Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network having a plurality of network parameters and being configured to process an input data item to generate a feature representation comprising a values for each...