Standard Deviation-Based Quantization for Deep Neural Networks. (arXiv:2202.12422v1 [cs.LG])

Quantization of deep neural networks is a promising approach that reduces the
inference cost, making it feasible to run deep networks on resource-restricted
devices. Inspired by existing methods, we propose a new framework to learn the
quantization intervals (discrete values) using the knowledge of the network's
weight and activation distributions, i.e., standard deviation. Furthermore, we
propose a novel base-2 logarithmic quantization scheme to quantize weights to
power-of-two discrete values. Our proposed scheme allows us to replace
resource-hungry high-precision multipliers with …

arxiv deviation networks neural networks quantization standard