US Patent Issued to INTERNATIONAL BUSINESS MACHINES on June 23 for "Contrastive learning by dynamically selecting dropout ratios and locations based on reinforcement learning" (Chinese Inventors)

ALEXANDRIA, Va., July 15 -- United States Patent no. 12,664,424, issued on June 23, was assigned to INTERNATIONAL BUSINESS MACHINES Corp. (Armonk, N.Y.).

"Contrastive learning by dynamically selecting dropout ratios and locations based on reinforcement learning" was invented by Zhong Fang Yuan (Xi'an, China), Si Tong Zhao (Beijing), Tong Liu (Xi'An, China), Yi Chen Zhong (Shanghai), Yuan Yuan Ding (Shanghai) and Hai Bo Zou (Beijing).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method for contrastive learning by selecting dropout ratios and locations based on reinforcement learning includes receiving training data having a positive sample corresponding to a target and negative samples not corresponding to ...