ALEXANDRIA, Va., July 28 -- United States Patent no. 12,694,266, issued on July 28, was assigned to PUSAN NATIONAL UNIVERSITY INDUSTRY-UNIVERSITY COOPERATION FOUNDATION (Busan, South Korea).

"Correlation recurrent unit for improving prediction performance of time-series data and correlation recurrent neural network" was invented by Hye Rim Bae (Busan, South Korea), Sung-hyun Sim (Busan, South Korea), Do Hee Kim (Busan, South Korea) and Han Seok Kang (Busan, South Korea).

According to the abstract* released by the U.S. Patent & Trademark Office: "A correlation recurrent unit and a correlation recurrent neural network are provided. An aspect provides a new neural network structure for training each decomposed time-series component by decomp...