ALEXANDRIA, Va., Aug. 20 -- United States Patent no. 12,393,404, issued on Aug. 19, was assigned to Huazhong University of Science and Technology (Wuhan, China).
"Sample-difference-based method and system for interpreting deep-learning model for code classification" was invented by Zhen Li (Wuhan, China), Ruqian Zhang (Wuhan, China), Deqing Zou (Wuhan, China), Hai Jin (Wuhan, China) and Yangrui Li (Wuhan, China).
According to the abstract* released by the U.S. Patent & Trademark Office: "A sample-difference-based method and system for interpreting a deep-learning model for code classification is provided, wherein the method includes a step of off-line training an interpreter: constructing code transformation for every code sample in a tra...