An adaptive inference method for crossbar (AIDX) is presented based on an optimization scheme for adjusting the duration and amplitude of input voltage pulses. AIDX minimizes the long-term effects of memristance drift on artificial neural network accuracy. The sub-threshold behavior of memristor has been modeled and verified by comparing with fabricated device data. The proposed method has been evaluated by testing on different network structures and applications, e.g., image reconstruction and classification tasks. The results showed an average of 60% improvement in convolutional neural network (CNN) performance on CIFAR10 dataset after 10000 inference operations as well as 78.6% error reduction in image reconstruction.

中文翻译：

---

AIDX：用于减轻忆阻 VMM 加速器中的状态漂移的自适应推理方案

基于用于调整输入电压脉冲的持续时间和幅度的优化方案，提出了交叉开关的自适应推理方法（AIDX）。AIDX 最大限度地减少了忆阻漂移对人工神经网络准确性的长期影响。通过与制造的器件数据进行比较，对忆阻器的亚阈值行为进行了建模和验证。已通过对不同网络结构和应用（例如图像重建和分类任务）的测试来评估所提出的方法。结果表明，经过 10000 次推理操作后，卷积神经网络 (CNN) 在 CIFAR10 数据集上的性能平均提高了 60%，图像重建的错误减少了 78.6%。