US Patent Issued to The University of Chicago on March 17 for "Training artificial neural networks using context-dependent gating with weight stabilization" (Illinois Inventors)

ALEXANDRIA, Va., March 17 -- United States Patent no. 12,579,440, issued on March 17, was assigned to The University of Chicago (Chicago).

"Training artificial neural networks using context-dependent gating with weight stabilization" was invented by Nicolas Y. Masse (Chicago), Gregory D. Grant (Chicago) and David J. Freedman (Chicago).

According to the abstract* released by the U.S. Patent & Trademark Office: "A computing device may receive a first set of training data for training an ANN to predict output data for a first task, and may train the ANN with the first set of training data by only adjusting values of weights associated with a first subset of neurons, the first subset selected based on an identity of the first task. The comput...