US Patent Issued to DeepMind Technologies on March 18 for "Training a neural network using outputs of a corruption neural network" (British Inventors)

ALEXANDRIA, Va., March 19 -- United States Patent no. 12,254,678, issued on March 18, was assigned to DeepMind Technologies Ltd. (London).

"Training a neural network using outputs of a corruption neural network" was invented by Dan-Andrei Calian (London), Sven Adrian Gowal (Cambridge, Great Britain), Timothy Arthur Mann (Harpenden, Great Britain) and Andras Gyorgy (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 processing a network input using a trained neural network with network parameters to generate an output for a machine learning task. The training includes: receiving a set of training examples eac...