Recent advances in emerging neuromorphic computing and perception devices

Abstract

Abstract Brain-inspired electronics represent a promising paradigm to resolve the energy and time bottlenecks in conventional digital machines. Recent advances have spanned both computing and sensing by imitating naturally evolved biological approaches, and the emerging neuromorphic computing and perception devices are recognized as the building blocks for implementing so-called in-memory and in-sensor computing. Therefore, it is urgent to review recent achievements regarding these devices and provide a perspective for future development. In this review, the recent advances in emerging neuromorphic computing and perception devices are summarized by explicating the structures and working mechanisms of two- and three-terminal synaptic devices. Inspiring applications in brain-inspired computing, prosthetics, and robotics, which shed light on the future development of this area, are also outlined. The challenges that need to be addressed are also discussed. It is expected that the advances in neuromorphic computing and perception devices will offer new opportunities toward autonomous artificial intelligence and neurorobotics.