Search Results for author:
Found 2 papers, 0 papers with code
Forget the Learning Rate, Decay Loss
In the usual deep neural network optimization process, the learning rate is the most important hyper parameter, which greatly affects the final convergence effect.
Fast, Better Training Trick --- Random Gradient
In this paper, we will show an unprecedented method to accelerate training and improve performance, which called random gradient (RG).
Cannot find the paper you are looking for? You can
Submit a new open access paper.
