36 citations · 141 across the 18 of their papers we have counts for
Showing 2018Show all
2 papers · 1 filter
cs.LG2018
Training Neural Networks Using Features Replay
Zhouyuan Huo, Bin Gu, Heng Huang
Training a neural network using backpropagation algorithm requires passing error gradients sequentially through the network. The backward locking prevents us from updating network…
cs.LG2018
Decoupled Parallel Backpropagation with Convergence Guarantee
Zhouyuan Huo, Bin Gu, Qian Yang +1
Backpropagation algorithm is indispensable for the training of feedforward neural networks. It requires propagating error gradients sequentially from the output layer all the way b…