US Patent Issued to NVIDIA on July 14 for "Techniques for correcting prediction errors in neural networks" (California Inventors)

ALEXANDRIA, Va., July 14 -- United States Patent no. 12,682,212, issued on July 14, was assigned to NVIDIA Corp. (Santa Clara, Calif.).

"Techniques for correcting prediction errors in neural networks" was invented by Prakash Gurumurthy (Sunnyvale, Calif.), Mu-Heng Yang (San Jose, Calif.), Yan Breek (Santa Clara, Calif.), Avinash Vem (Santa Clara, Calif.) and Fay Wang (San Jose, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "One or more arithmetic logic circuits to at least partially cause a neural network to be trained by replacing one or more activations generated by one or more layers of the neural network with ground truth data depending on how accurate the one or more activations are predicted to ...