3 citations · 3 across the 2 of their papers we have counts for
2 papers
cs.LG2019★ 3 cited
Mean Shift Rejection: Training Deep Neural Networks Without Minibatch Statistics or Normalization
Brendan Ruff, Taylor Beck, Joscha Bach
Deep convolutional neural networks are known to be unstable during training at high learning rate unless normalization techniques are employed. Normalizing weights or activations a…
cs.CV2017
Deep Control - a simple automatic gain control for memory efficient and high performance training of deep convolutional neural networks
Brendan Ruff
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 er…