no code implementations • 7 May 2019 • Yang Jiang, Cong Zhao, Zeyang Dou, Lei Pang
Based on this correlation, we further demonstrate that, though the reward of NAS is sparse, the policy gradient method implicitly assign the reward to all operations and skip connections based on the sampling frequency.
no code implementations • 31 Jul 2017 • Yang Jiang, Zeyang Dou, Qun Hao, Jie Cao, Kun Gao, Xi Chen
In this paper, we propose the nonlinearity generation method to speed up and stabilize the training of deep convolutional neural networks.