Coexistence of short-and long-term memory in NbO_(x)-based memristor for a nonlinear reservoir computing system  

作　　者：Heeseong Jang Jungang Heo Jihee Park Hyesung Na Sungjun Kim 

机构地区：[1]Division of Electronics and Electrical Engineering,Dongguk University,Seoul 04620,Republic of Korea

出　　处：《Frontiers of physics》2025年第1期125-136,共12页物理学前沿(英文版)

基　　金：supported in part by the National Research Foundation of Korea(NRF)grant funded by the Ministry of Science and ICT(RS-2024-00356939 and RS-2024-00405691).

摘　　要：In this study,TiN/NbO_(x)/Pt memristor devices with short-term memory(STM)and self-rectifying characteristics are used for reservoir computing.The STM characteristics of the device are detected using direct current sweep and pulse transients.The self-rectifying characteristics of the device can be explained by the work function differences between the TiN and Pt electrodes.Furthermore,neural network simulations were conducted for pattern recognition accuracy when the conductance was used as the synaptic weight.The emulation of synaptic memory and forgetfulness by short-term memory effects are demonstrated using paired-pulse facilitation and excitatory postsynaptic potential.The efficient training reservoir computing consisted of all 16 states(4-bit)in the memristor device as a physical reservoir and the artificial neural network simulation as a readout layer and yielded a pattern recognition accuracy of 92.34%for the modified National Institute of Standards and Technology dataset.Finally,it is found that STM and long-term memory in the device coexist by adjusting the intensity of pulse stimulation.

关 键 词：MEMRISTOR resistive switching neural network reservoir computing 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]