ALEXANDRIA, Va., Sept. 15 -- United States Patent no. 12,737,608, issued on Sept. 15, was assigned to NVIDIA Corp. (Santa Clara, Calif.).

"Deep hierarchical variational autoencoder" was invented by Arash Vahdat (Mountain View, Calif.) and Jan Kautz (Lexington, Mass.).

According to the abstract* released by the U.S. Patent & Trademark Office: "One embodiment of the present invention sets forth a technique for performing machine learning. The technique includes inputting a training dataset into a variational autoencoder (VAE) comprising an encoder network, a prior network, and a decoder network. The technique also includes training the VAE by updating one or more parameters of the VAE based on a smoothness of one or more outputs produced by...