Robust Processing-In-Memory Neural Networks via Noise-Aware Normalization

Abstract

Analog computing hardwares, such as Processing-in-memory (PIM) accelerators, have gradually received more attention for accelerating the neural network computations. However, PIM accelerators often suffer from intrinsic noise in the physical components, making it challenging for neural network models to achieve the same performance as on the digital hardware. Previous works in mitigating intrinsic noise assumed the knowledge of the noise model, and retraining the neural networks accordingly was required. In this paper, we propose a noise-agnostic method to achieve robust neural network performance against any noise setting. Our key observation is that the degradation of performance is due to the distribution shifts in network activations, which are caused by the noise. To properly track the shifts and calibrate the biased distributions, we propose a "noise-aware" batch normalization layer, which is able to align the distributions of the activations under variational noise inherent in the analog environments. Our method is simple, easy to implement, general to various noise settings, and does not need to retrain the models. We conduct experiments on several tasks in computer vision, including classification, object detection and semantic segmentation. The results demonstrate the effectiveness of our method, achieving robust performance under a wide range of noise settings, more reliable than existing methods. We believe that our simple yet general method can facilitate the adoption of analog computing devices for neural networks.

arXiv comment7 pages, 3 figure

References in corpus (7)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• YOLOv3: An Incremental Improvement
• Deep Residual Learning for Image Recognition
• Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs
• Convergence of Adversarial Training in Overparametrized Neural Networks
• Four Things Everyone Should Know to Improve Batch Normalization
• Noisy Machines: Understanding Noisy Neural Networks and Enhancing Robustness to Analog Hardware Errors Using Distillation

Cited by in corpus (4)

• Examining the Role and Limits of Batchnorm Optimization to Mitigate Diverse Hardware-noise in In-memory Computing
• Picking Up Quantization Steps for Compressed Image Classification
• Post-Training BatchNorm Recalibration
• ThRIve: Thermally Robust CNN Inference via Low-Rank Adaptation in Heterogeneous PIM Architectures