US Patent Issued to NVIDIA on Dec. 16 for "Efficient identification of critical faults in neuromorphic hardware of a neural network" (North Carolina Inventors)

ALEXANDRIA, Va., Dec. 16 -- United States Patent no. 12,499,369, issued on Dec. 16, was assigned to NVIDIA Corp. (Santa Clara, Calif.).

"Efficient identification of critical faults in neuromorphic hardware of a neural network" was invented by Ching-Yuan Chen (Chapel Hill, N.C.) and Krishnendu Chakrabarty (Chapel Hill, N.C.).

According to the abstract* released by the U.S. Patent & Trademark Office: "The disclosure provides misclassification-driven training (MDT) that efficiently identifies critical faults in neuromorphic hardware, such as a memristor crossbar. MDT advantageously identifies whether a hardware fault is a critical fault and can be used to limit fault recovery when a hardware fault is not a critical fault. By applying fault-t...