US Patent Issued to ShanghaiTech University on Dec. 9 for "Deep neural network checkpoint optimization system and method based on non-volatile memory" (Chinese Inventors)

ALEXANDRIA, Va., Dec. 9 -- United States Patent no. 12,493,801, issued on Dec. 9, was assigned to ShanghaiTech University (Shanghai).

"Deep neural network checkpoint optimization system and method based on non-volatile memory" was invented by Shu Yin (Shanghai), Tianyuan Wu (Shanghai) and Yuanhao Li (Shanghai).

According to the abstract* released by the U.S. Patent & Trademark Office: "Deep neural network checkpoint optimization system and method based on non-volatile memory are provided, where the client module and the server module register corresponding network structures in non-volatile memory and create data indexes and data communication protocols based on remote direct memory access (RDMA) before the start of training deep neural n...