US Patent Issued to Intel on July 22 for "System and method for balancing sparsity in weights for accelerating deep neural networks" (California, Arizona Inventors)

ALEXANDRIA, Va., July 23 -- United States Patent no. 12,367,380, issued on July 22, was assigned to Intel Corp. (Santa Clara, Calif.).

"System and method for balancing sparsity in weights for accelerating deep neural networks" was invented by Arnab Raha (Santa Clara, Calif.), Debabrata Mohapatra (San Jose, Calif.), Deepak Abraham Mathaikutty (Chandler, Ariz.), Raymond Jit-Hung Sung (San Francisco) and Cormac Michael Brick (San Francisco).

According to the abstract* released by the U.S. Patent & Trademark Office: "An apparatus is provided to access a weight vector of a layer in a sequence of layers in the DNN. The weight vector includes a first sequence of weights having different values. A bitmap is generated based on the weight vector. T...