211 citations · 1.4k across the 61 of their papers we have counts for
Showing 2019 · cs.LGShow all
3 papers · 2 filters
cs.LG2019★ 1 cited
Dynamic Routing Networks
Shaofeng Cai, Yao Shu, Wei Wang +1
The deployment of deep neural networks in real-world applications is mostly restricted by their high inference costs. Extensive efforts have been made to improve the accuracy with…
cs.LG2019★ 54 cited
Effective and Efficient Dropout for Deep Convolutional Neural Networks
Shaofeng Cai, Yao Shu, Gang Chen +3
Convolutional Neural networks (CNNs) based applications have become ubiquitous, where proper regularization is greatly needed. To prevent large neural network models from overfitti…
cs.LG2019★ 21 cited
Model Slicing for Supporting Complex Analytics with Elastic Inference Cost and Resource Constraints
Shaofeng Cai, Gang Chen, Beng Chin Ooi +1
Deep learning models have been used to support analytics beyond simple aggregation, where deeper and wider models have been shown to yield great results. These models consume a hug…