no code implementations • 29 Nov 2019 • Brendan Ruff, Taylor Beck, Joscha Bach
This new technique allows direct training of the test graph so that training and test models are identical.
no code implementations • 13 Jun 2017 • 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 error and leads to slow and sub-optimal training.