Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations

  title={Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations},
  author={Itay Hubara and Matthieu Courbariaux and Daniel Soudry and Ran El-Yaniv and Yoshua Bengio},
  journal={Journal of Machine Learning Research},
We introduce a method to train Quantized Neural Networks (QNNs) — neural networks with extremely low precision (e.g., 1-bit) weights and activations, at run-time. At traintime the quantized weights and activations are used for computing the parameter gradients. During the forward pass, QNNs drastically reduce memory size and accesses, and replace most arithmetic operations with bit-wise operations. As a result, power consumption is expected to be drastically reduced. We trained QNNs over the… CONTINUE READING
Highly Influential
This paper has highly influenced 31 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 381 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 64 times over the past 90 days. VIEW TWEETS


Publications citing this paper.
Showing 1-10 of 242 extracted citations

381 Citations

Citations per Year
Semantic Scholar estimates that this publication has 381 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 71 references

Binarized neural networks for language modeling

  • Weiyi Zheng, Yina Tang
  • Technical Report cs224d, Stanford University,
  • 2016
1 Excerpt

Similar Papers

Loading similar papers…