US Patent Issued to GOOGLE on Nov. 3 for "Utilizing elastic weight consolidation (EWC) loss term(s) to mitigate catastrophic forgetting in training machine learning model(s)" (California Inventors)

ALEXANDRIA, Va., Nov. 3 -- United States Patent no. 12,783,956, issued on Nov. 3, was assigned to GOOGLE LLC (Mountain View, Calif.).

"Utilizing elastic weight consolidation (EWC) loss term(s) to mitigate catastrophic forgetting in training machine learning model(s)" was invented by Andrew Hard (Menlo Park, Calif.), Kurt Partridge (San Francisco), Sean Augenstein (San Mateo, Calif.) and Rajiv Mathews (Sunnyvale, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Processor(s) of a client device can receive global weights of a global ML model from a remote system, obtain a client device data set, determine a Fisher information matrix for the client data set, and transmit the Fisher information matrix for th...