End-to-End Learning of Energy-Constrained Deep Neural Networks

By Haichuan Yang, Yuhao Zhu, Ji Liu. 2018

14 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Zhangyang Wang
2. Yue Wang
3. Yingyan Lin
4. Ting-Wu Chin
5. Tan Minh Nguyen
6. Diana Marculescu
7. Tan Y. Nguyen
8. Yang Zhao

Citations in the corpus

• Layer-compensated Pruning for Resource-constrained Convolutional Neural Networks (2018, methodology): “For example, past work has used (cid:96) 2 of filter weights (He et al., 2018a; Yang et al., 2018b), (cid:96) 1 of filter weights (Mao et al., 2017; Li et al., 2017), (cid:96) 2 of filter weights and filter weights of the next layer (Jiang et al., 2018), first-order Taylor expansion on the loss…”
• EnergyNet: Energy-Efficient Dynamic Inference (2018, methodology): “While both methods 32 [2, 13] show promising results towards pursuing more energy-efficient CNN models, they do not 33 incorporate energy costs into the training loss function to explicitly learn a more energy-efficient 34 model.”