Noise-Agnostic One-Shot Training and Retraining for Robust DNN Inferencing on Analog Compute-in-Memory Systems

Analog Compute-in-Memory (ACiM) architectures are a promising alternatives to traditional von Neumann-based systems for accelerating deep neural networks (DNNs), as they alleviate the memory bottleneck by performing in-situ matrixvector multiplications. However, the analog nature of computation in ACiM makes DNNs highly susceptible to noise and process variations. To mitigate the effects of analog noise, existing approaches rely on variation-aware or noise-aware training, retraining, or fine-tuning. These methods, however, are not scalable, as they require chip-specific retraining and typically involve separate training runs for different levels of noise tolerance. Moreover, they overlook the inherent fault tolerance of analog-to-digital converters (ADCs). To address these limitations, we propose a one-shot training and retraining strategy for robust DNN inferencing on ACiM platforms. Our method is guided by a detailed analysis of error propagation through ADCs, revealing that robustness can be enhanced by strategically reshaping the weight distribution to better align with ADC resilience characteristics. Simulation results and experimental results with fabricated chips show that the proposed method improves inferencing accuracy by 70%−90% for ResNet-18 and DenseNet-121 under 70% noise injection on CIFAR-10 and SVHN, and by 50%-80% for VGG-16 under 50% noise. These gains are achieved with only a 5% energy overhead due to the modified weight distribution.

@inproceedings{bommana2026noiseagnostic,
  author    = {Ashish Reddy Bommana and Ben Feinberg and T. Patrick Xiao and Christopher H. Bennett and Matthew J. Marinella and Krishnendu Chakrabarty},
  title     = {{Noise-Agnostic One-Shot Training and Retraining for Robust DNN Inferencing on Analog Compute-in-Memory Systems}},
  booktitle = {Asia and South Pacific Design Automation Conference (ASP-DAC)},
  year      = {2026},
  month     = {jan},
  address   = {Tokyo, Japan},
  doi       = {10.1109/ASP-DAC66049.2026.11420230}
}