The High Performance, Low Power Promise Of Neuromorphic Computing

Neuromorphic computing is an emerging technology that mimics the human brain and promises both extraordinary performance and transformative energy efficiency. It is based on the so-called von Neumann architecture and uses silicon artificial neurons to form a spiking neural network (SNN) that performs event-triggered computation. This approach has the potential to achieve high-performance computing (HPC) while consuming 1/1000th of the energy. It could be used to reduce the power consumption of machine learning and AI neural network models and revolutionize the hardware system for data-centric computing.