US Patent Issued to Microsoft Technology Licensing on March 24 for "Adjusting precision and topology parameters for neural network training based on a performance metric" (Washington Inventors)

ALEXANDRIA, Va., March 24 -- United States Patent no. 12,585,926, issued on March 24, was assigned to Microsoft Technology Licensing LLC (Redmond, Wash.).

"Adjusting precision and topology parameters for neural network training based on a performance metric" was invented by Bita Darvish Rouhani (Bellevue, Wash.), Eric S. Chung (Woodinville, Wash.), Daniel Lo (Bothell, Wash.) and Douglas C. Burger (Bellevue, Wash.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Apparatus and methods for training neural networks based on a performance metric, including adjusting numerical precision and topology as training progresses are disclosed. In some examples, block floating-point formats having relatively lower accuracy ...