Deep reservoir computing based on self-rectifying memristor synapse for time series prediction

Herein, a self-rectifying resistive switching memristor synapse with a Ta/NbOx/Pt structure was demonstrated for deep reservoir computing (RC). The memristor demonstrated stable nonlinear analog switching characteristics, with a rectification ratio of up to 1.6 x 10(5), good endurance, and high uniformity. Additionally, the memristor exhibited typical short-term plasticity and dynamic synaptic characteristics. Based on these characteristics, a deep memristor RC system was proposed for time series prediction. The system achieved a low normalized root mean square error (NRMSE) of 0.04 in the time series prediction of the Henon map. Even at 90 degrees C, deep RC retains good predictive power with an NRMSE of only 0.07. This work provides guidance for efficient deep memristive RC networks to handle more complex future temporal tasks.

Automated summary

A self-rectifying resistive switching memristor synapse with a Ta/NbOx/Pt structure was demonstrated for deep reservoir computing. The memristor exhibited stable nonlinear analog switching characteristics, with a rectification ratio of up to 1.6 x 10(5), good endurance, and high uniformity. Based on these characteristics, a deep memristor reservoir computing system achieved a low normalized root mean square error (NRMSE) of 0.04 in time series prediction and retained good predictive power even at 90 degrees C with an NRMSE of 0.07.