A Monolayer Leaky Integrate‐and‐Fire Neuron for 2D Memristive Neuromorphic Networks

Abstract

Abstract 2D material based memristors have exhibited superior performance as artificial synapses for neuromorphic computing. However, 2D artificial neurons as have note been exploited as an indispensable computational element owing to the rich dynamics of neurons, which impede the construction of a 2D neuromorphic network. A methodology is developed by introducing ionic migration dynamics and electrochemical reaction into monolayer MoS2 single crystal and a 2D artificial neuron is realized. The sophisticated electrophysiology process of leaky integrate‐and‐fire (LIF) is emulated by the injection and extraction of Ag+ ions under an e‐field in a monolayer MoS2 device with fine‐tuned channel length. Moreover, the fire frequency and relaxation time of the artificial neurons can be readily modulated by adjusting the input voltage pulses. By directly capturing conductive filament under a scanning electron microscope, the underlying mechanism of the unique resistive switching of the 2D artificial neuron is attributed to the rapid diffusion and migration of Ag in MoS2 lattice under the e‐field. The formation and rupture of the conductive Ag filament enable volatile resistive switching and LIF behaviors. Furthermore, MoS2‐based neurons are integrated with a nonvolatile synapse array to build a full memristive artificial neural network and implement pattern classification, paving the way for the construction of 2D neuromorphic networks.

Keywords

• 2D materials
• artificial neurons
• chemical vapor deposition
• memristors
• neuromorphic networks
• molybdenum disulfide