US Patent Issued to NEC on June 23 for "System, method and non-transitory computer readable medium for convolutional neural network model optimization targeting blackbox hardware" (Japanese Inventor)

ALEXANDRIA, Va., July 15 -- United States Patent no. 12,664,398, issued on June 23, was assigned to NEC Corp. (Tokyo).

"System, method and non-transitory computer readable medium for convolutional neural network model optimization targeting blackbox hardware" was invented by Darshit Vaghani (Tokyo).

According to the abstract* released by the U.S. Patent & Trademark Office: "An object is to provide a tiling based convolutional NN model optimizing system for blackbox hardware. The system including performing means (11) for changing a size of data and performing a convolutional NN operation included in a first convolutional NN model on the data, managing means (12) for managing the size of data in association with inference time when the con...