US Patent Issued to Google on Sept. 8 for "Fine-tuning computer vision neural networks using task rewards" (Swiss, British Inventors)

ALEXANDRIA, Va., Sept. 8 -- United States Patent no. 12,731,392, issued on Sept. 8, was assigned to Google LLC (Mountain View, Calif.).

"Fine-tuning computer vision neural networks using task rewards" was invented by Alexander Kolesnikov (Zurich), Xiaohua Zhai (Zurich), Andre Susano Pinto (Zurich), Yuge Shi (London) and Lucas Klaus Beyer (Zurich).

According to the abstract* released by the U.S. Patent & Trademark Office: "Methods, systems, and apparatus, including computer programs encoded on computer storage media, for fine-tuning a computer vision neural network. In particular, the neural network is fine-tuned using task rewards and through reinforcement learning."

The patent was filed on Feb. 9, 2024, under Application No. 18/438,317....