ALEXANDRIA, Va., Dec. 16 -- United States Patent no. 12,499,662, issued on Dec. 16, was assigned to Google LLC (Mountain View, Calif.).
"Dynamic training of models" was invented by Anthony Jacob Piergiovanni (Denver), Weicheng Kuo (Santa Clara, Calif.), Wei Li (Fremont, Calif.) and Anelia Angelova (Palo Alto, Calif.).
According to the abstract* released by the U.S. Patent & Trademark Office: "A method involves the training of a model by dynamically adjusting the number of examples within each training batch. The dynamic adjustment is accomplished by adjusting the number of examples per task within each training batch according to the performance of the model on the tasks that the model is being trained on. In some embodiments, this method...