ALEXANDRIA, Va., Feb. 24 -- United States Patent no. 12,561,965, issued on Feb. 24, was assigned to Synaptics Inc. (San Jose, Calif.).
"Neural network caching for video" was invented by Dmitri Lvov (Ramat Hasharon, Israel) and Maor Shliefer (Herzliya, Israel).
According to the abstract* released by the U.S. Patent & Trademark Office: "This disclosure provides methods, devices, and systems for machine learning. The present implementations more specifically relate to techniques for reducing the computational load of a convolutional neural network (CNN) when processing successive video frames. In some aspects, a machine learning system may cache or store the outputs (also referred to as "activations") produced by one or more layers of a CNN ...