Preliminary investigation on the implementation of an artificial synapse using TaOx-based memristor with thermally oxidized active layer.

Abstract

This study presents a preliminary exploration of thermally oxidized TaOx-based memristors and their potential as artificial synapses. Unlike the 10-minannealed devices, which display instability due to current overshoots, the 5-minannealed device exhibits stable resistive switching, retention, and endurance characteristics. Moreover, our memristor showcases synaptic behaviors encompassing potentiation, depression, spike-timing-dependent plasticity, and excitatory postsynaptic currents. This synaptic emulation holds tremendous promise for applications in neuromorphic computing, offering the opportunity to replicate the adaptive learning principles observed in biological synapses. In addition, we evaluate the device's suitability for pattern recognition within a neural network using the modified National Institute of Standards and Technology dataset. Our assessment reveals that the Pt/TaOx/Ta memristor with an oxidized insulator achieves outstanding potential manifested by an accuracy of 93.25% for the identical pulse scheme and an impressive accuracy of 95.42% for the incremental pulse scheme.