US Patent Issued to International Business Machines on May 20 for "Generating data based on pre-trained models using generative adversarial models" (New York, Massachusetts Inventors)

ALEXANDRIA, Va., June 16 -- United States Patent no. 12,307,377, issued on May 20, was assigned to International Business Machines Corp. (Armonk, N.Y.).

"Generating data based on pre-trained models using generative adversarial models" was invented by Wang Zhou (White Plains, N.Y.), Yang Zhang (Cambridge, Mass.) and Shiyu Chang (Elmsford, N.Y.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Techniques for generator model training are provided. A classifier model that was trained using one or more data samples in a target class is received, and a generative adversarial network (GAN) is trained to generate simulated data samples for the target class, comprising: generating a first simulated data sample using a g...