US Patent Issued to Google on July 29 for "Training neural network systems to perform multiple machine learning tasks" (American, Swiss Inventors)

ALEXANDRIA, Va., July 30 -- United States Patent no. 12,373,694, issued on July 29, was assigned to Google LLC (Mountain View, Calif.).

"Training neural network systems to perform multiple machine learning tasks" was invented by Andrea Gesmundo (Zurich) and Jeffrey Adgate Dean (Palo Alto, Calif.).

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 system to perform multiple machine learning tasks."

The patent was filed on March 14, 2024, under Application No. 18/605,700.

*For further information, including images, charts and tables, please visit: http://patft.uspto.gov/netacgi/nph-Parser?...