US Patent Issued to NVIDIA on Feb. 10 for "Hyperparameter optimization using one or more neural networks" (California, Pennsylvania, Maryland, Idaho Inventors)

ALEXANDRIA, Va., Feb. 11 -- United States Patent no. 12,548,312, issued on Feb. 10, was assigned to NVIDIA Corp. (Santa Clara, Calif.).

"Hyperparameter optimization using one or more neural networks" was invented by Yufan He (Philadelphia), Dong Yang (Pocatello, Idaho), Andriy Myronenko (San Francisco) and Daguang Xu (Potomac, Md.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Apparatuses, systems, and techniques are presented to train neural networks. In at least one embodiment, one or more hyperparameters are adjusted in conjunction with one or more weight parameters corresponding to one or more neural networks."

The patent was filed on Aug. 9, 2022, under Application No. 17/884,012.

*For further informa...