Recent progress on optoelectronic synaptic devices

Abstract

Neuromorphic (brain-like) computing has great potential to solve the von Neumann bottleneck due to its self-adaptive learning, high-parallel computing capability, and low-power consumption. Realization of neuromorphic computing depends on the development of synaptic devices that mimic biological synapses. Initially, synaptic devices were electronic, and such devices face significant challenges relative to optimization of bandwidth, connectivity, and density. It has been recently shown that the incorporation of light to make optoelectronic synaptic devices brings new opportunities for the development of synaptic devices. On one hand, light enables high bandwidth, low crosstalk, low energy consumption, and no delay. On the other hand, optoelectronic devices can be used to simulate special neurobehavioral functions, such as vision. As the basis of optoelectronic integrated neural networks, optoelectronic synaptic devices are expected to greatly contribute to the development of high-performance and low-power neuromorphic computing. In this review we introduce the basic properties of optoelectronic synaptic devices. Different types and applications that have been reported for optoelectronic devices are discussed. In addition, future prospects for the development of optoelectronic synaptic devices is outlined.