Corpus ID: 220496077

Term Revealing: Furthering Quantization at Run Time on Quantized DNNs

@article{Kung2020TermRF,
  title={Term Revealing: Furthering Quantization at Run Time on Quantized DNNs},
  author={H. T. Kung and Bradley McDanel and S. Zhang},
  journal={ArXiv},
  year={2020},
  volume={abs/2007.06389}
}

H. T. Kung, Bradley McDanel, S. Zhang

Published 2020

Computer Science

ArXiv

We present a novel technique, called Term Revealing (TR), for furthering quantization at run time for improved performance of Deep Neural Networks (DNNs) already quantized with conventional quantization methods. TR operates on power-of-two terms in binary expressions of values. In computing a dot-product computation, TR dynamically selects a fixed number of largest terms to use from the values of the two vectors in the dot product. By exploiting normal-like weight and data distributions… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed