ALEXANDRIA, Va., Oct. 28 -- United States Patent no. 12,450,477, issued on Oct. 21, was assigned to Western Digital Technologies Inc. (San Jose, Calif.).

"Adversarial information bottleneck strategy for improved machine learning" was invented by Qing Li (Milpitas, Calif.), Yongjune Kim (Daegu, South Korea) and Cyril Guyot (San Jose, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Certain aspects of the present disclosure provide techniques for performing machine learning, including: processing a training data instance with a task model to generate an encoding and a task model output; processing a discriminator input based on the encoding using a discriminator model to generate an estimated mutual infor...