Atomically Thin Synaptic Devices for Optoelectronic Neuromorphic Vision

TLDR

Emerging atomically thin materials offer electrical and optical properties that can be harnessed to create imaging sensors with built‑in processing, paving the way for low‑latency, energy‑efficient artificial vision systems. The study reports atomically thin β‑In₂S₃ nanosheets that exhibit persistent photoconductivity under ultraviolet and visible light. The authors fabricated β‑In₂S₃ nanosheets with persistent photoconductivity and demonstrated their use as optoelectronic synaptic devices by implementing a convolutional neural network for image classification. The persistent photoconductivity enables β‑In₂S₃‑based devices to mimic biological synapse dynamics, with the effect attributed to intrinsic defects, and the platform supports scalable vision‑sensory neural networks for multispectral imaging and neuromorphic computation.

Abstract

Abstract Imaging sensors with inbuilt processing capability are expected to form the backbone of low‐latency and highly energy efficient artificial vision systems. A range of emerging atomically thin materials provide opportunities to exploit their electrical and optical properties for human vision and brain inspired functions. This work reports atomically thin nanosheets of β‐In 2 S 3 which exhibit inherent persistent photoconductivity (PPC) under ultraviolet and visible wavelengths. This PPC effect enables β‐In 2 S 3 ‐based optoelectronic devices to optically mimic the dynamics of biological synapses. Based on the material characterizations, the PPC effect is attributed to the intrinsic defects in the synthesized β‐In 2 S 3 nanosheet. Furthermore, the feasibility of adopting these atomically thin synaptic devices for optoelectronic neuromorphic hardware is demonstrated by implementing a convolutional neural network for image classification. As such, the demonstrated atomically thin nanosheets and optoelectronic synaptic devices provide a platform for scaling up complex vision‐sensory neural networks, which can find many promising applications for multispectral imaging and neuromorphic computation.