Bit Error Robustness in PyTorch Article Series

I was planning to have an article series on bit error robustness in deep learning — similar to my article series on adversarial robustness — with accompanying PyTorch code. However, the recent progress in machine learning made me focus on other projects. Nevertheless, the articles should have been:

  • Simple Fixed-Point Quantization for DNNs in PyTorch
  • 4.5% Test Error on CIFAR10 with 4-Bit Fixed-Point Quantization
  • Implementing Fast Bitwise Operations for PyTorch
  • Testing Robustness Against Bit Errors in Quantized DNN Weights
  • Weight Clipping for Improved Bit Error Robustness
  • Random Bit Error Training in PyTorch

Large parts of this repository are taken from my latest MLSys'21 [1] and TPAMI'22 [2] papers:

PyTorch code on GitHub
  • [1] D. Stutz, N. Chandramoorthy, M. Hein, B. Schiele. Bit Error Robustness for Energy-Efficient DNN Accelerators. MLSys, 2021.
  • [2] D. Stutz, N. Chandramoorthy, M. Hein, B. Schiele. Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Accelerators. TPAMI, 2022.