US Patent Issued to NVIDIA on June 3 for "Training neural networks with limited data using invertible augmentation operators" (Finnish Inventors)

ALEXANDRIA, Va., June 4 -- United States Patent no. 12,321,825, issued on June 3, was assigned to NVIDIA Corp. (Santa Clara, Calif.).

"Training neural networks with limited data using invertible augmentation operators" was invented by Tero Tapani Karras (Helsinki), Miika Samuli Aittala (Helsinki), Janne Johannes Hellsten (Helsinki), Samuli Matias Laine (Vantaa, Finland), Jaakko T. Lehtinen (Helsinki) and Timo Oskari Aila (Tuusula, Finland).

According to the abstract* released by the U.S. Patent & Trademark Office: "Embodiments of the present disclosure relate to a technique for training neural networks, such as a generative adversarial neural network (GAN), using a limited amount of data. Training GANs using too little example data typica...