1 code implementation • 4 Jun 2020 • Zana Rashidi, Kasra Ahmadi K. A., Aijun An, Xiaogang Wang
We propose a novel and efficient momentum-based first-order algorithm for optimizing neural networks which uses an adaptive coefficient for the momentum term.
no code implementations • ICLR 2018 • Ricky Fok, Aijun An, Zana Rashidi, Xiaogang Wang
We propose a Warped Residual Network (WarpNet) using a parallelizable warp operator for forward and backward propagation to distant layers that trains faster than the original residual neural network.