btgraham / Batchwise-Dropout

Run fully connected artificial neural networks with dropout applied (mini)batchwise, rather than samplewise. Given two hidden layers each subject to 50% dropout, the corresponding matrix multiplications for forward- and back-propagation is 75% less work as the dropped out units are not calculated.

Batchwise Dropout Benjamin Graham, University of Warwick, 2015 GPLv3

If you use this software please tell me what you are using it for ([e-mail]).

Run "make dataset" for dataset in the list { mnist, cifar10, artificial }