US Patent Issued to Tobii on March 18 for "Autoencoding generative adversarial network for augmenting training data usable to train predictive models" (Swedish Inventor)

ALEXANDRIA, Va., March 19 -- United States Patent no. 12,254,414, issued on March 18, was assigned to Tobii AB (Danderyd, Sweden).

"Autoencoding generative adversarial network for augmenting training data usable to train predictive models" was invented by Marten Nilsson (Danderyd, Sweden).

According to the abstract* released by the U.S. Patent & Trademark Office: "Techniques for using a deep generative model to generate synthetic data sets that can be used to boost the performance of a discriminative model are described. In an example, an autoencoding generative adversarial network (AEGAN) is trained to generate the synthetic data sets. The AEGAN includes an autoencoding network and a generative adversarial network (GAN) that share a gene...