US Patent Issued to Northeastern University on Feb. 17 for "Computer-implemented methods and systems for DNN weight pruning for real-time execution on mobile devices" (Massachusetts Inventors)

ALEXANDRIA, Va., Feb. 17 -- United States Patent no. 12,554,987, issued on Feb. 17, was assigned to Northeastern University (Boston).

"Computer-implemented methods and systems for DNN weight pruning for real-time execution on mobile devices" was invented by Yanzhi Wang (Newton Highlands, Mass.) and Xiaolong Ma (Boston).

According to the abstract* released by the U.S. Patent & Trademark Office: "A computer-implemented method is disclosed for compressing a deep neural network (DNN) model by DNN weight pruning to accelerate DNN inference on mobile devices. The method includes the steps of (a) performing an intra-convolution kernel pruning of the DNN model wherein a fixed number of weights are pruned in each convolution kernel of the DNN mode...