US Patent Issued to NOTA on Oct. 14 for "Method of lightweighting a neural network for object recognition, a method of recognizing object using the lightweighted neural network, and an electronic device for performing the same" (South Korean Inventors)

ALEXANDRIA, Va., Oct. 21 -- United States Patent no. 12,443,828, issued on Oct. 14, was assigned to NOTA INC. (Daejeon, South Korea).

"Method of lightweighting a neural network for object recognition, a method of recognizing object using the lightweighted neural network, and an electronic device for performing the same" was invented by Hyungjun Lee (Daejeon, South Korea) and Hancheol Park (Daejeon, South Korea).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method of compressing a neural network model for object recognition according to an embodiment of the present application includes: receiving an original model for object recognition trained based on a first data set; receiving a second data set of an an...