Compute-in-memory (CIM) accelerators built upon non-volatile memory (NVM) devices excel in energy efficiency and latency when performing Deep Neural Network (DNN) inference, thanks to their in-situ data processing capability. However, the stochastic nature and intrinsic variations of NVM devices often result in performance degradation in DNN inference. Introducing these non-ideal device behaviors during DNN training enhances robustness, but drawbacks include limited accuracy improvement, reduced prediction confidence, and convergence issues. This arises from a mismatch between the deterministic training and non-deterministic device variations, as such training, though considering variations, relies solely on the model's final output. In this work, we draw inspiration from the control theory and propose a novel training concept: Negative Feedback Training (NFT) leveraging the multi-scale noisy information captured from network. We develop two specific NFT instances, Oriented Variational Forward (OVF) and Intermediate Representation Snapshot (IRS). Extensive experiments show that our methods outperform existing state-of-the-art methods with up to a 46.71% improvement in inference accuracy while reducing epistemic uncertainty, boosting output confidence, and improving convergence probability. Their effectiveness highlights the generality and practicality of our NFT concept in enhancing DNN robustness against device variations.

翻译：基于非易失性存储设备的存内计算加速器凭借其原位数据处理能力，在深度神经网络推理中展现出卓越的能效和延迟优势。然而，非易失性存储设备的随机特性与固有偏差常导致深度神经网络推理性能下降。在训练过程中引入这些非理想器件行为虽能增强模型鲁棒性，但存在精度提升有限、预测置信度降低及收敛性问题等缺陷。这源于确定性训练与非确定性器件偏差之间的不匹配——此类训练虽考虑了偏差因素，却仅依赖模型最终输出。本研究受控制理论启发，提出一种全新训练概念：负反馈训练（Negative Feedback Training, NFT），通过捕获网络中的多尺度噪声信息实现鲁棒性提升。我们开发了两种具体的NFT实例：定向变分前馈（Oriented Variational Forward, OVF）和中间表征快照（Intermediate Representation Snapshot, IRS）。大量实验表明，本方法在推理精度上较现有最优方法提升高达46.71%，同时降低了认知不确定性、增强了输出置信度并提升了收敛概率。其有效性凸显了NFT概念在提升深度神经网络对抗器件偏差鲁棒性方面的普适性与实用性。