US Patent Issued to InterDigital VC Holdings on May 19 for "Low displacement rank based deep neural network compression" (California Inventors)

ALEXANDRIA, Va., May 19 -- United States Patent no. 12,632,723, issued on May 19, was assigned to InterDigital VC Holdings Inc. (Wilmington, Del.).

"Low displacement rank based deep neural network compression" was invented by Fabien Racape (San Francisco), Swayambhoo Jain (Milpitas, Calif.), Shahab Hamidi-Rad (Sunnyvale, Calif.) and Dimitris Papadimitriou (Berkeley, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method and an apparatus for performing deep neural network compression use an approximation training set along with information, such as in matrices representing weights, biases and non-linearities, to iteratively compress a pre-trained deep neural network by low displacement rank based appr...