US Patent Issued to Numenta on March 25 for "Performing inference and training using sparse neural network" (California Inventors)

ALEXANDRIA, Va., March 26 -- United States Patent no. 12,260,337, issued on March 25, was assigned to Numenta Inc. (Redbwood City, Calif.).

"Performing inference and training using sparse neural network" was invented by Subutai Ahmad (Palo Alto, Calif.) and Luiz Scheinkman (Sunnyvale, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "An inference system trains and performs inference using a sparse neural network. The sparse neural network may include one or more layers, and each layer may be associated with a set of sparse weights that represent sparse connections between nodes of a layer and nodes of a previous layer. A layer output may be generated by applying the set of sparse weights associated with ...