Zephon Blog

09-01

动态神经网络相关的几篇论文

06-09

《MCUNetV2:Memory-Efficient Patch-based Inference for Tiny Deep Learning》

05-07

《TinyTL:Reduce Memory,Not Parameters for Efficient On-Device Learning》

05-05

《MEST:Accurate and Fast Memory-Economic Sparse Training Framework on the Edge》

05-04

《ALBERT:A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS》

05-03

《From Dense to Sparse:Contrastive Pruning for Better Pre-trained Language Model Compression》

04-28

《Channel Pruning for Accelerating Very Deep Neural Networks》

04-27

《PRUNING CONVOLUTIONAL NEURAL NETWORKS FOR RESOURCE EFFICIENT INFERENCE》

04-26

《PRUNING FILTERS FOR EFFICIENT CONVNETS》

04-25

《Learning Structured Sparsity in Deep Neural Networks》