Neural networks based on memristive devices have achieved great progress recently. However, memristive synapses with nonlinearity and asymmetry seriously limit the classification accuracy. Moreover, insufficient number of training samples in many cases also have negative effect on the classification accuracy of neural networks due to overfitting. In this work, dropout neuronal units are developed based on stochastic volatile memristive devices of Ag/Ta₂O₅:Ag/Pt. The memristive neural network using the dropout neuronal units effectively solves the problem of overfitting and mitigates the negative effects of the nonideality of memristive synapses, eventually achieves a classification accuracy comparable to the theoretical limit. The stochastic and volatile switching performances of the Ag/Ta₂O₅:Ag/Pt device are attributed to the stochastical rupture of the Ag filament under high electrical stress in the Ta₂O₅ layer, according to the TEM observation and the kinetic Monte Carlo simulation.

中文翻译：

---

高分类精度的神经网络中基于随机忆阻器的失落神经元单元的实现

基于忆阻器件的神经网络最近取得了长足的进步。但是，具有非线性和不对称性的忆阻突触严重限制了分类精度。此外，在许多情况下，训练样本数量不足也会由于过度拟合而对神经网络的分类精度产生负面影响。在这项工作中，基于Ag / Ta ₂ O _5的随机挥发性忆阻器件开发了辍学神经元单元。：银/铂 使用丢失的神经元单元的忆阻神经网络有效地解决了过拟合问题并减轻了忆阻突触非理想性的负面影响，最终实现了与理论极限相当的分类精度。根据TEM观察和动力学Monte ，Ag / Ta ₂ O ₅：Ag / Pt器件的随机和挥发性开关性能归因于Ta ₂ O ₅层中高电应力下Ag丝在高电应力下的随机断裂。卡洛模拟。