Skip to main content
Search

# ASDL (Accelerated Signed Digit Loading)

1 related articles

Subscribe to updates
  1. arXiv

    ASDL trims CNN coefficients to about 1.5 active bits: ImageNet accuracy slips from 81.3% to 80.41% with no retraining

    Multiply-accumulates dominate convolutional-network inference, and each one can be rewritten as a handful of shift-and-adds whose count equals the number of signed powers of two (SPT) in the coefficient. ASDL replaces the earlier greedy routine that inserted one SPT per step with a routine that fills an entire bit plane per step, converting faster than MPGBP on ResNet50's longest coefficient vector while keeping a lower approximation error. Applied to pre-trained CNN coefficients, it leaves about 1.5 active bits per coefficient on average and moves ImageNet accuracy from 81.3% to 80.41% without retraining or calibration.

You’re all caught up