US Patent Issued to Samsung Electronics on March 24 for "System and method for designing efficient super resolution deep convolutional neural networks by cascade network training, cascade network trimming, and dilated convolutions" (California Inventors)

ALEXANDRIA, Va., March 24 -- United States Patent no. 12,585,949, issued on March 24, was assigned to Samsung Electronics Co. Ltd (South Korea).

"System and method for designing efficient super resolution deep convolutional neural networks by cascade network training, cascade network trimming, and dilated convolutions" was invented by Haoyu Ren (San Diego), Mostafa El-Khamy (San Diego) and Jungwon Lee (San Diego).

According to the abstract* released by the U.S. Patent & Trademark Office: "Apparatuses and methods of manufacturing same, systems, and methods are described. In one aspect, a method includes generating a convolutional neural network (CNN) by training a CNN having a plurality of convolutional layers, and performing cascade train...