Device-aware inference operations in SONOS nonvolatile memory arrays

2020 
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.
    • Correction
    • Source
    • Cite
    • Save
    • Machine Reading By IdeaReader
    15
    References
    6
    Citations
    NaN
    KQI
    []