US Patent Issued to Adobe on June 23 for "Multitask machine-learning model training and training data augmentation" (California, Washington Inventors)

ALEXANDRIA, Va., July 15 -- United States Patent no. 12,664,463, issued on June 23, was assigned to Adobe Inc. (San Jose, Calif.).

"Multitask machine-learning model training and training data augmentation" was invented by Khalil Mrini (La Jolla, Calif.), Franck Dernoncourt (Spokane, Wash.), Seunghyun Yoon (San Jose, Calif.), Trung Huu Bui (San Jose, Calif.), Walter W. Chang (San Jose, Calif.), Emilia Farcas (San Diego) and Ndapandula T. Nakashole (Del Mar, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Multitask machine-learning model training and training data augmentation techniques are described. In one example, training is performed for multiple tasks simultaneously as part of training a multitask...