Corpus ID: 1518846

BinaryConnect: Training Deep Neural Networks with binary weights during propagations

@inproceedings{Courbariaux2015BinaryConnectTD,
  title={BinaryConnect: Training Deep Neural Networks with binary weights during propagations},
  author={Matthieu Courbariaux and Yoshua Bengio and J. David},
  booktitle={NIPS},
  year={2015}
}
Deep Neural Networks (DNN) have achieved state-of-the-art results in a wide range of tasks, with the best results obtained with large training sets and large models. [...] Key Method We introduce BinaryConnect, a method which consists in training a DNN with binary weights during the forward and backward propagations, while retaining precision of the stored weights in which gradients are accumulated. Like other dropout schemes, we show that BinaryConnect acts as regularizer and we obtain near state-of-the-art…Expand
Training and Inference with Integers in Deep Neural Networks
PXNOR: Perturbative Binary Neural Network
  • Vlad Pelin, I. Radoi
  • Computer Science
  • 2019 18th RoEduNet Conference: Networking in Education and Research (RoEduNet)
  • 2019
BINARY DEEP NEURAL NETWORKS
Training High-Performance and Large-Scale Deep Neural Networks with Full 8-bit Integers
Espresso: Efficient Forward Propagation for Binary Deep Neural Networks
Simultaneously Optimizing Weight and Quantizer of Ternary Neural Network Using Truncated Gaussian Approximation
  • Zhezhi He, Deliang Fan
  • Computer Science, Mathematics
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2019
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 53 REFERENCES
ImageNet classification with deep convolutional neural networks
DaDianNao: A Machine-Learning Supercomputer
  • Yunji Chen, Tao Luo, +8 authors O. Temam
  • Computer Science
  • 2014 47th Annual IEEE/ACM International Symposium on Microarchitecture
  • 2014
DianNao: a small-footprint high-throughput accelerator for ubiquitous machine-learning
Fixed-point feedforward deep neural network design using weights +1, 0, and −1
Deep Learning with Limited Numerical Precision
X1000 real-time phoneme recognition VLSI using feed-forward deep neural networks
A highly scalable Restricted Boltzmann Machine FPGA implementation
...
1
2
3
4
5
...