Spike-shape dependence of the spike-timing dependent synaptic plasticity in ferroelectric-tunnel-junction synapses
Spike-shape dependence of the spike-timing dependent synaptic plasticity in ferroelectric-tunnel-junction synapses
复制标题
DOI：
10.1038/s41598-019-54215-w
复制
发表时间：
2019-11-28
影响因子：
4.6
通讯作者：
Sawa, A.
中科院分区：
文献类型：
--
作者：
Stoliar, P.;Yamada, H.;Sawa, A.
电阻开关（RS）器件由于其非易失性和模拟电阻变化而越来越受到神经网络人工突触应用的关注。在神经网络中，基于spike- time -dependent plasticity （STDP）的spike neural network （SNN）是一种高能效的神经网络。为了在电阻开关器件中实现STDP，迄今为止已经提出了几种类型的电压尖峰，但是关于STDP特性和尖峰类型之间关系的报道很少。在这里，我们报告了几种类型的尖峰在铁电隧道结（ftj）中实现的STDP特性。基于模拟叠加尖峰的时间演变，并考虑到ftj的非线性电流-电压（I-V）特性，我们提出了从峰值振幅（V-peak）和持续时间(t（p)和t(d)）的尖峰参数模拟电导变化幅度（Delta G(max)）和时间窗口（tau(C)）的STDP曲线参数的方程：三角形-三角形、矩形-三角形和矩形-矩形。STDP的功耗实验显示，突触非活动条件下（峰值定时竖条δ t竖条> tau(C)）的功耗是突触活动条件下（竖条δ t竖条< tau(C)）的50-82%。这一发现表明，应该降低非活动突触条件下的功耗，以使使用ftj作为突触实现的SNN的总功耗最小化。
Resistive switching (RS) devices have attracted increasing attention for artificial synapse applications in neural networks because of their nonvolatile and analogue resistance changes. Among the neural networks, a spiking neural network (SNN) based on spike-timing-dependent plasticity (STDP) is highly energy efficient. To implement STDP in resistive switching devices, several types of voltage spikes have been proposed to date, but there have been few reports on the relationship between the STDP characteristics and spike types. Here, we report the STDP characteristics implemented in ferroelectric tunnel junctions (FTJs) by several types of spikes. Based on simulated time evolutions of superimposed spikes and taking the nonlinear current-voltage (I-V) characteristics of FTJs into account, we propose equations for simulating the STDP curve parameters of a magnitude of the conductance change (Delta G(max)) and a time window (tau(C)) from the spike parameters of a peak amplitude (V-peak) and time durations (t(p) and t(d)) for three spike types: triangle-triangle, rectangular-triangle, and rectangular-rectangular. The power consumption experiments of the STDP revealed that the power consumption under the inactive-synapse condition (spike timing vertical bar Delta t vertical bar > tau(C)) was as large as 50-82% of that under the active-synapse condition (vertical bar Delta t vertical bar < tau(C)). This finding indicates that the power consumption under the inactive-synapse condition should be reduced to minimize the total power consumption of an SNN implemented by using FTJs as synapses.