ALEXANDRIA, Va., June 16 -- United States Patent no. 12,307,750, issued on May 20, was assigned to Microsoft Technology Licensing LLC (Redmond, Wash.).
"Scalable knowledge distillation techniques for machine learning" was invented by Adit Krishnan (Mountain View, Calif.), Ji Li (San Jose, Calif.), Yixuan Wei (Beijing), Xiaozhi Yu (San Jose, Calif.), Han Hu (Beijing) and Qi Dai (Beijing).
According to the abstract* released by the U.S. Patent & Trademark Office: "A data processing system implements a dynamic knowledge distillation process including dividing training data into a plurality of batches of samples and distilling a student model from a teacher model using an iterative knowledge distillation. The process includes instantiating an...