ALEXANDRIA, Va., June 16 -- United States Patent no. 12,657,900, issued on June 16, was assigned to QUALCOMM Inc. (San Diego).
"Multi-task transfer learning using weight divergence constraints" was invented by Simon Ekman Von Huth (Nacka, Sweden), Mohammadreza Malek-Mohammadi (Solna, Sweden) and Saeed Dabbaghchian (Bromma, Sweden).
According to the abstract* released by the U.S. Patent & Trademark Office: "Certain aspects of the present disclosure provide techniques and apparatus for training a machine learning model based on transfer learning and weight divergence constraints. The method generally includes receiving weight information associated with a machine learning model, wherein the machine learning model comprises a model trained t...