ALEXANDRIA, Va., June 17 -- United States Patent no. 12,314,857, issued on May 27, was assigned to ACER Inc. (New Taipei, Taiwan).
"Method and device for deep neural network compression" was invented by Juinn-Dar Huang (New Taipei, Taiwan), Ya-Chu Chang (New Taipei, Taiwan) and Wei-Chen Lin (New Taipei, Taiwan).
According to the abstract* released by the U.S. Patent & Trademark Office: "A method for deep neural network compression is provided. The method includes: using at least one weight of a deep neural network (DNN), setting a value of a P parameter, and combining every P weights in groups, and perform branch pruning and retraining, so that only one of each group has a non-zero weight, and the remaining weights are 0, wherein the rema...