Search Results for author:
Found 2 papers, 0 papers with code
Mean Shift Rejection: Training Deep Neural Networks Without Minibatch Statistics or Normalization
This new technique allows direct training of the test graph so that training and test models are identical.
Deep Control - a simple automatic gain control for memory efficient and high performance training of deep convolutional neural networks
Training a deep convolutional neural net typically starts with a random initialisation of all filters in all layers which severely reduces the forward signal and back-propagated error and leads to slow and sub-optimal training.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
