ALEXANDRIA, Va., June 6 -- United States Patent no. 12,282,857, issued on April 22, was assigned to Google LLC (Mountain View, Calif.).
"Relative margin for contrastive learning" was invented by Siyuan Qiao (Santa Clara, Calif.), Chenxi Liu (Santa Clara, Calif.), Jiahui Yu (Bellevue, Wash.) and Yonghui Wu (Fremont, Calif.).
According to the abstract* released by the U.S. Patent & Trademark Office: "Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training neural networks through contrastive learning. In particular, the contrastive learning is modified to use a relative margin to adjust a training pair's contribution to optimization."
The patent was filed on Sept. 27, 2024, under Appli...