US Patent Issued to Google on July 15 for "Training neural networks using data augmentation policies" (California Inventors)

ALEXANDRIA, Va., July 16 -- United States Patent no. 12,361,326, issued on July 15, was assigned to Google LLC (Mountain View, Calif.).

"Training neural networks using data augmentation policies" was invented by Jonathon Shlens (San Francisco), Quoc V. Le (Sunnyvale, Calif.), Ekin Dogus Cubuk (Sunnyvale, Calif.) and Barret Zoph (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 machine learning model. One of the methods includes obtaining a training data set for training a machine learning model, the training data set comprising a plurality of training inputs; determining a plurality of d...