US Patent Issued to INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF SCIENCES on March 25 for "Feature extraction system, method and apparatus based on neural network optimization by gradient filtering" (Chinese Inventors)

ALEXANDRIA, Va., March 26 -- United States Patent no. 12,260,660, issued on March 25, was assigned to INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF SCIENCES (Beijing).

"Feature extraction system, method and apparatus based on neural network optimization by gradient filtering" was invented by Yang Chen (Beijing), Guanxiong Zeng (Beijing) and Shan Yu (Beijing).

According to the abstract* released by the U.S. Patent & Trademark Office: "A feature extraction system, method and apparatus based on neural network optimization by gradient filtering is provided. The feature extraction method includes: acquiring, by an information acquisition device, input information; constructing, by a feature extraction device, different feature extraction network...