Login / Signup
GXNOR-Net: Training deep neural networks with ternary weights and activations without full-precision memory under a unified discretization framework.
Lei Deng
Peng Jiao
Jing Pei
Zhenzhi Wu
Guoqi Li
Published in:
Neural Networks (2018)
Keyphrases
</>
neural network
main contribution
theoretical framework
text classification
weighted sum
data sets
genetic algorithm
linear combination
test set
high precision
main memory
recurrent neural networks
neural nets
multi layer
unified model