ALEXANDRIA, Va., Jan. 13 -- United States Patent no. 12,524,674, issued on Jan. 13, was assigned to GOOGLE LLC (Mountain View, Calif.).
"Subtask adaptable neural network" was invented by Raviteja Vemulapalli (Seattle), Jianrui Cai (Cupertino, Calif.), Bradley Ray Green (Bellevue, Wash.), Ching-Hui Chen (Shoreline, Wash.) and Lior Shapira (Redmond, Wash.).
According to the abstract* released by the U.S. Patent & Trademark Office: "At training time, a base neural network can be trained to perform each of a plurality of basis subtasks included in a total set of basis subtasks (e.g., individually or some combination thereof). Next, a description of a desired combined subtask can be obtained. Based on the description of the combined subtask, a...