ALEXANDRIA, Va., Feb. 3 -- United States Patent no. 12,541,570, issued on Feb. 3, was assigned to Nvidia Corp. (Santa Clara, Calif.).
"Unsupervised domain adaptation with neural networks" was invented by David Acuna Marrero (Toronto), Guojun Zhang (Waterloo, Canada), Marc Law (Ontario, Canada) and Sanja Fidler (Toronto).
According to the abstract* released by the U.S. Patent & Trademark Office: "Approaches presented herein provide for unsupervised domain transfer learning. In particular, three neural networks can be trained together using at least labeled data from a first domain and unlabeled data from a second domain. Features of the data are extracted using a feature extraction network. A first classifier network uses these features to...