no code implementations • 19 Apr 2023 • Xuanyu He, Yu-I Yang, Ran Song, Jiachen Pu, Conggang Hu, Feijun Jiang, Wei zhang, Huanghao Ding
Statistically, the structure of a winning subnetwork guarantees an approximately optimal ratio in this regime.
no code implementations • 27 May 2020 • Hongwei Xie, Shuo Zhang, Huanghao Ding, Yafei Song, Baitao Shao, Conggang Hu, Ling Cai, Mingyang Li
The inherent heavy computation of deep neural networks prevents their widespread applications.