US Patent Issued to SOUTHEAST UNIVERSITY on April 22 for "Method and system for quantifying semantic variance between neural network representations" (Chinese Inventors)

ALEXANDRIA, Va., June 6 -- United States Patent no. 12,283,082, issued on April 22, was assigned to SOUTHEAST UNIVERSITY (Nanjing, China).

"Method and system for quantifying semantic variance between neural network representations" was invented by Hao Chen (Nanjing, China) and Haoran Zhou (Nanjing, China).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method and system for quantifying semantic variance between neural network representations is provided. Two neural network representations to be compared are first extracted, the weight of each filter in an intermediate layer corresponding to each semantic concept is learned on a reference dataset using the Net2Vec method, then set IoU of each representation f...