US Patent Issued to GOOGLE on May 12 for "Scalable transfer learning with expert models" (Swiss Inventors)

ALEXANDRIA, Va., May 12 -- United States Patent no. 12,626,194, issued on May 12, was assigned to GOOGLE LLC (Mountain View, Calif.).

"Scalable transfer learning with expert models" was invented by Carlos Riquelme Ruiz (Zurich), Andre Susano Pinto (Zurich), Joan Puigcerver (Zurich), Basil Mustafa (Zurich), Neil Matthew Tinmouth Houlsby (Zurich), Sylvain Gelly (Kilchberg, Switzerland), Cedric Benjamin Renggli (Uster, Switzerland) and Daniel Martin Keysers (Stallikon, Switzerland).

According to the abstract* released by the U.S. Patent & Trademark Office: "Generally, the present disclosure is directed to systems and methods that provide a simple, scalable, yet effective strategy to perform transfer learning with a mixture of experts (MoE). ...