US Patent Issued to Imagination Technologies on Jan. 20 for "Methods and systems for converting weights of a deep neural network from a first number format to a second number format" (British Inventors)

ALEXANDRIA, Va., Jan. 20 -- United States Patent no. 12,530,569, issued on Jan. 20, was assigned to Imagination Technologies Ltd. (Kings Langley, Great Britain).

"Methods and systems for converting weights of a deep neural network from a first number format to a second number format" was invented by Cagatay Dikici (London), Paul Brasnett (West Molesey, Great Britain), Muhammad Asad (London) and Stephen Morphet (St. Albans, Great Britain).

According to the abstract* released by the U.S. Patent & Trademark Office: "Methods and system for converting a plurality of weights of a filter of a Deep Neural Network (DNN) in a first number format to a second number format, the second number format having less precision than the first number format, ...