PaperReview
Introduction
Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
Binarized Neural Networks
Trained Ternary Quantization
DSD
INCREMENTAL NETWORK QUANTIZATION
Distilling the Knowledge in a Neural Network
Learning bothWeights and Connections for Efficient Neural Networks
BinaryConnect
Googlenet
SqueezeNet
vgg
Deep Residual Learning
Powered by
GitBook
DSD
DSD: DENSE-SPARSE-DENSE TRAINING FOR DEEP
NEURAL NETWORKS
https://arxiv.org/abs/1607.04381
results matching "
"
No results matching "
"
