US Patent Issued to Google on May 5 for "Training neural networks using learned optimizers" (California Inventors)

ALEXANDRIA, Va., May 5 -- United States Patent no. 12,619,879, issued on May 5, was assigned to Google LLC (Mountain View, Calif.).

"Training neural networks using learned optimizers" was invented by Luke Shekerjian Metz (Mountain View, Calif.), Niruban Maheswaranathan (San Jose, Calif.), Christian Daniel Freeman (San Francisco), Benjamin Poole (Palo Alto, Calif.) and Jascha Narain Sohl-Dickstein (San Francisco).

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. One of the methods includes performing, using a plurality of training examples, a training step to obtain respective gradients o...