Controlled Memory and Threshold Switching Behaviors in a Heterogeneous Memristor for Neuromorphic Computing

Abstract

The fully memristive neural network is emerging as a game‐changer in the artificial intelligence competition. Artificial synapses and neurons, as two fundamental elements for hardware neural networks, have been substantially implemented by different devices with memory and threshold switching (TS) behaviors, respectively. However, obtaining controllable memory and TS behaviors in the same memristive material system is still a considerable challenge that holds great potential for realizing compatible artificial neurons and synapses. Here, a heterogeneous bilayer conductive filamentary memristor comprising two different electrolytes with distinct copper ion mobility is reported: Cu/GeTe/Al2O3/Pt, which can demonstrate the governance of switching types. Experimentally, when the thickness of the Al2O3 layer is 3 nm, stable nonvolatile multilevel memory switching (MS) is observed and employed to mimic the synaptic plasticity. With increasing oxide thickness, the switching behavior under the same compliance current alters from MS to volatile TS and is used to emulate the integrate‐and‐fire neuron function. The controllable switching stems from the change in the metal filament morphology within the Al2O3 layer, which is supported by ab initio calculation results. This method enables a new pathway for constructing functionally reconfigurable neuromorphic devices for intelligence neuromorphic systems.

‘Stateful’ threshold switching for neuromorphic learning

“…27–31 In addition, the conversion between TS and RS under programmed stimuli like compliance current was believed to be due to the manipulated morphology of nanofilaments. 32–34 However, the ‘stateful’ TS working in the millivolt range here has been undiscovered up to now to the best of our knowledge.…”

Artificial Neurons Based on Ag/V2C/W Threshold Switching Memristors

“…We assume that the higher diffusion coefficient of Ag ions in V 2 C may enhance the diffusive process of Ag for threshold switching and emulate faster and more controllable neurons [45,56,57]. In conclusion, the superior strength-modulated spike frequency characteristic has been successfully implemented, which may strengthen the feasibility of MXene-based artificial neurons for neuromorphic systems [18,[58][59][60].…”

Artificial Neurons and Synapses Based on Al/a-SiNxOy:H/P+-Si Device with Tunable Resistive Switching from Threshold to Memory

“…In the long term, the realization of controllable MS and TS characteristics in the same Si-based resistive switching system remains a great challenge, which can guarantee the lower cost for fabrication of the neuromorphic chip [ 18 , 19 , 20 ]. Until now, the material scope of TS memory was mainly limited to oxide-based material such as HfO 2 [ 18 , 21 ], Al 2 O 3 [ 22 ], NiO [ 23 , 24 ], which dependents on the metal conductive pathway. According to the references [ 8 , 9 ], the precise control of ion migration in the resistive switching devices is the performance selection criteria for neuromorphic applications.…”