ALEXANDRIA, Va., Aug. 12 -- United States Patent no. 12,387,098, issued on Aug. 12, was assigned to Ford Global Technologies LLC (Dearborn, Mich.).
"Multi-task learning" was invented by Meghana Laxmidhar Gaopande (Sunnyvale, Calif.) and Nikita Jaipuria (Pittsburgh).
According to the abstract* released by the U.S. Patent & Trademark Office: "A computer that includes a processor and a memory, the memory including instructions executable by the processor to execute a multi-task learning (MTL) neural network that includes multi-task layers and single-task layers, and that is configured to receive an image as input to a first one of the multi-task layers and to output respective predictions for each of a plurality of tasks from respective ones...