US Patent Issued to GDM Holding on July 14 for "Neural network systems implementing conditional neural processes for efficient learning" (British, Canadian, Japanese Inventors)

ALEXANDRIA, Va., July 14 -- United States Patent no. 12,682,244, issued on July 14, was assigned to GDM Holding LLC (Mountain View, Calif.).

"Neural network systems implementing conditional neural processes for efficient learning" was invented by Tiago Miguel Sargento Pires Ramalho (Tokyo), Dan Rosenbaum (London), Marta Garnelo Abellanas (London), Christopher Maddison (Toronto), Seyed Mohammadali Eslami (London), Yee Whye Teh (Oxford, Great Britain) and Danilo Jimenez Rezende (London).

According to the abstract* released by the U.S. Patent & Trademark Office: "According to a first aspect a network system to generate output data values from input data values according to one or In more learned data distributions comprises an input to recei...