US Patent Issued to Georgia Tech Research on Aug. 25 for "Fully analog compute-in-memory architecture for neural networks" (North Carolina, Georgia Inventors)

ALEXANDRIA, Va., Aug. 25 -- United States Patent no. 12,717,873, issued on Aug. 25, was assigned to Georgia Tech Research Corp. (Atlanta).

"Fully analog compute-in-memory architecture for neural networks" was invented by Laith A. Shamieh (Charlotte, N.C.) and Saibal Mukhopadhyay (Atlanta).

According to the abstract* released by the U.S. Patent & Trademark Office: "A Fully Analog STate-Space Compute-In-Memory (FAST-CIM) architecture implements cascaded CIM arrays that maintain continuous analog signal flow throughout neural network computations. Sequential data patches are processed through cascaded CIM arrays, where a feedforward CIM array performs initial vector-matrix multiplication using analog computations within memory cells, and the...