In this paper, we study the inference accuracy of the Resistive Random Access Memory (ReRAM) neuromorphic circuit due to stuck-at faults (stuck-on, stuck-off, and stuck at a certain resistive value). A simulation framework using Python is used to perform supervised machine learning (neural network with 3 hidden layers, 1 input layer, and 1 output layer) of handwritten digits and construct a corresponding fully analog neuromorphic circuit (4 synaptic arrays) simulated by Spectre. A generic 45nm Process Development Kit (PDK) was used. We study the difference in the inference accuracy degradation due to stuck-on and stuck-off defects. Various defect patterns are studied including circular, ring, row, column, and circular-complement defects. It is found that stuck-on and stuck-off defects have a similar effect on inference accuracy. However, it is also found that if there is a spatial defect variation across the columns, the inference accuracy may be degraded significantly. We also propose a machine learning (ML) strategy to recover the inference accuracy degradation due to stuck-at faults. The inference accuracy is improved from 48% to 85% in a defective neuromorphic circuit.

翻译：本文研究了阻变随机存取存储器（ReRAM）神经形态电路因固定故障（固定导通、固定关断以及固定在某电阻值）导致的推理精度问题。我们采用基于Python的仿真框架，对手写数字进行监督机器学习（具有3个隐藏层、1个输入层和1个输出层的神经网络），并利用Spectre仿真构建相应的全模拟神经形态电路（4个突触阵列），使用通用45纳米工艺开发套件（PDK）。我们分析了固定导通和固定关断缺陷对推理精度退化的差异性影响，研究了包括圆形、环形、行、列及圆形互补缺陷在内的多种缺陷模式。研究发现固定导通与固定关断缺陷对推理精度的影响相似，但若列方向上存在空间缺陷变异，推理精度可能显著下降。我们还提出一种机器学习策略来补偿固定故障导致的推理精度退化，使缺陷神经形态电路的推理精度从48%提升至85%。