论文标题
Sonos中的设备感知推理操作非易失性存储器阵列
Device-aware inference operations in SONOS nonvolatile memory arrays
论文作者
论文摘要
非挥发记忆阵列可以将预训练的神经网络模型用于边缘推理。但是，这些系统受设备级噪声和保留问题的影响。在这里，我们检查了由这些影响造成的损害，引入了缓解策略，并证明了其在制造的Sonos（硅氧化二氮 - 氧化物）设备中的用途。在MNIST，时尚摄影和CIFAR-10任务上，我们的方法增加了对突触噪声和漂移的弹性。我们还可以通过5-8位精度来实现强大的性能。
Non-volatile memory arrays can deploy pre-trained neural network models for edge inference. However, these systems are affected by device-level noise and retention issues. Here, we examine damage caused by these effects, introduce a mitigation strategy, and demonstrate its use in fabricated array of SONOS (Silicon-Oxide-Nitride-Oxide-Silicon) devices. On MNIST, fashion-MNIST, and CIFAR-10 tasks, our approach increases resilience to synaptic noise and drift. We also show strong performance can be realized with ADCs of 5-8 bits precision.
