US Patent Issued to Northeastern University, College of William & Mary on May 12 for "Computer-implemented methods and systems for compressing recurrent neural network (RNN) models and accelerating RNN execution in mobile devices to achieve real-time inference" (Massachusetts, Virginia Inventors)

ALEXANDRIA, Va., May 12 -- United States Patent no. 12,626,131, issued on May 12, was assigned to Northeastern University (Boston) and College of William & Mary (Williamsburg, Va.).

"Computer-implemented methods and systems for compressing recurrent neural network (RNN) models and accelerating RNN execution in mobile devices to achieve real-time inference" was invented by Yanzhi Wang (Newton Highlands, Mass.), Peiyan Dong (Boston), Zhengang Li (Boston), Bin Ren (Jamestown, Va.) and Wei Niu (Jamestown, Va.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A recurrent neural network (RNN) acceleration framework leverages both a block-based pruning approach and compiler optimizations to accelerate RNN inference on...