US Patent Issued to Amazon Technologies on July 8 for "Machine learning model adaptation via segment replacement and student-teacher training" (Washington, California Inventors)

ALEXANDRIA, Va., July 9 -- United States Patent no. 12,353,971, issued on July 8, was assigned to Amazon Technologies Inc. (Seattle).

"Machine learning model adaptation via segment replacement and student-teacher training" was invented by Poorna Chand Srinivas Perumalla (Seattle), Nagajyothi Nookula (Seattle) and Long Gao (San Jose, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Techniques for machine learning (ML) model adaptation via segment replacement and student-teacher training are described. A model optimizer determines that a ML model sought to be deployed to an edge device includes a source segment that is not supported by the edge device. The model optimizer identifies a replacement segment ...