Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

@inproceedings{Courbariaux2016BinarizedNN,
  title={Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1},
  author={Matthieu Courbariaux and Itay Hubara and Daniel Soudry and Ran El-Yaniv and Yoshua Bengio},
  year={2016}
}
We introduce a method to train Binarized Neural Networks (BNNs) neural networks with binary weights and activations at run-time. At training-time the binary weights and activations are used for computing the parameters gradients. During the forward pass, BNNs drastically reduce memory size and accesses, and replace most arithmetic operations with bit-wise operations, which is expected to substantially improve power-efficiency. To validate the effectiveness of BNNs we conduct two sets of… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 377 CITATIONS, ESTIMATED 58% COVERAGE

658 Citations

02004002016201720182019
Citations per Year
Semantic Scholar estimates that this publication has 658 citations based on the available data.

See our FAQ for additional information.

Similar Papers

Loading similar papers…