Browsing by Subject "Variability-aware training"

Now showing 1 - 1 of 1
  • Thumbnail Image
    Item
    Variability-aware training and self-tuning of highly quantized DNNs for analog PIM
    (2021-12-03) Deng, Zihao; Orshansky, Michael; Erez, Mattan
    DNNs deployed on analog processing in memory (PIM) architectures are subject to fabrication-time variability. We developed a new joint variability- and quantization-aware DNN training algorithm for highly quantized analog PIM-based models that is significantly more effective than prior work. It outperforms variability-oblivious and post-training quantized models on multiple computer vision datasets/models. For low- bitwidth models and high variation, the gain in accuracy is up to 35.7% for ResNet-18 over the best alternative. We demonstrate that, under a realistic pattern of within- and between-chip components of variability, training alone is unable to prevent large DNN accuracy loss (of up to 54% on CIFAR- 100/ResNet-18). We introduce a self-tuning DNN architecture that dynamically adjusts layer-wise activations during inference and is effective in reducing accuracy loss to below 10%.