US Patent Issued to Google on May 12 for "Encoding and reconstructing inputs using neural networks" (California, Pennsylvania Inventors)

ALEXANDRIA, Va., May 12 -- United States Patent no. 12,626,102, issued on May 12, was assigned to Google LLC (Mountain View, Calif.).

"Encoding and reconstructing inputs using neural networks" was invented by Martin Abadi (Palo Alto, Calif.) and David Godbe Andersen (Pittsburgh).

According to the abstract* released by the U.S. Patent & Trademark Office: "Systems, methods, devices, and other techniques are described herein for training and using neural networks to encode inputs and to process encoded inputs, e.g., to reconstruct inputs from the encoded inputs. A neural network system can include an encoder neural network, a trusted decoder neural network, and an adversary decoder neural network. The encoder neural network processes a prima...