US Patent Issued to CAMBRICON TECHNOLOGIES on Sept. 23 for "Apparatus and methods for training in convolutional neural networks" (Chinese Inventors)

ALEXANDRIA, Va., Sept. 23 -- United States Patent no. 12,423,582, issued on Sept. 23, was assigned to CAMBRICON TECHNOLOGIES CORPORATION LIMITED (Beijing).

"Apparatus and methods for training in convolutional neural networks" was invented by Yunji Chen (Beijing), Tian Zhi (Beijing), Shaoli Liu (Beijing), Qi Guo (Beijing) and Tianshi Chen (Beijing).

According to the abstract* released by the U.S. Patent & Trademark Office: "Aspects for backpropagation of a convolutional neural network are described herein. The aspects may include a direct memory access unit configured to receive input data from a storage device and a master computation module configured to select one or more portions of the input data based on a predetermined convolution w...