US Patent Issued to TOYOTA RESEARCH INSTITUTE, THE BOARD OF TRUSTEES OF THE LELAND STANFORD JUNIOR UNIVERSITY on Sept. 23 for "Provable guarantees for self-supervised deep learning with spectral contrastive loss" (California Inventors)

ALEXANDRIA, Va., Sept. 23 -- United States Patent no. 12,423,961, issued on Sept. 23, was assigned to TOYOTA RESEARCH INSTITUTE INC. (Los Altos, Calif.) and THE BOARD OF TRUSTEES OF THE LELAND STANFORD JUNIOR UNIVERSITY (Stanford, Calif.).

"Provable guarantees for self-supervised deep learning with spectral contrastive loss" was invented by Jeff Z. Haochen (Stanford, Calif.), Colin Wei (Pleasanton, Calif.), Adrien David Gaidon (San Jose, Calif.) and Tengyu Ma (Stanford, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method for self-supervised learning is described. The method includes generating a plurality of augmented data from unlabeled image data. The method also includes generating a population...