Ntt Research Co-authored Publication Demonstrates Optically Accelerated Edge Computing

NTT Research, Inc., a division of NTT, has developed an approach to optically driven deep neural networks (DNN) called Netcast, which resolves the memory-access bottleneck in resource-constrained edge devices, enabling orders of magnitude energy and latency reduction. This was demonstrated in work performed by MIT Ph.D. candidate Alexander Sludds, under the joint supervision of Dr. Hamerly and MIT Professor Dirk Englund, and with the help of a wide group of collaborators. The research was published in the October 20 issue of Science. Netcast encodes the DNN model in an optical signal and streams it to the edge device, allowing for rapid classification of data and execution of other computationally intensive tasks.