Linear and symmetric synaptic weight update characteristics in van der Waals heterostructure transistors based on 2D In4/3P2Se6 barrier layer

Abstract

Two-dimensional van der Waals heterostructures with fast-switching speed and ultra-low power consumption are promising building blocks for artificial synaptic devices (ASD) that aim to solve problems faced by traditional computing. However, the nonlinearity and asymmetry of synaptic weight updates in artificial synapses have hindered the achievement of high image classification accuracy in most reported neuromorphic networks. Here, we develop a nonvolatile MoS2/In4/3P2Se6/graphene ASD with excellent performance. Due to the intrinsic low conduction band offset (0.86 eV) of MoS2/In4/3P2Se6, the vdW heterostructure device exhibits an ultra-large storage window of 71.2 V at ±40 V back-gate sweep, a low nonlinear factor of 0.014/0.042, and a low asymmetry factor at 0.028. Additionally, the device exhibits synaptic behaviors including excitatory postsynaptic current, pair-pulse facilitation, and important “learning-experience” synaptic function under electrical and optical stimulation. This work indicates that In4/3P2Se6 provides remarkable opportunities for band alignment-related applications and can facilitate ongoing research of neuromorphic functional electronics.