ALEXANDRIA, Va., Aug. 26 -- United States Patent no. 12,400,117, issued on Aug. 26, was assigned to UNIVERSITAT ZURICH (Zurich, Switzerland).
"Parameter-efficient method for training neural networks" was invented by Yuhuang Hu (Zurich, Switzerland) and Shih-Chii Liu (Zurich, Switzerland).
According to the abstract* released by the U.S. Patent & Trademark Office: "A computer-implemented method is used to adapt a first artificial neural network for data classification tasks. The first artificial neural network is characterized by a first number of first weight parameters, and includes a set of first network layers. The method includes freezing at least some of the first weight parameters of the first neural network to obtain frozen first we...