In their classic 2012 paper: Improving neural networks by preventing co-adaptation of feature detectors, Hinton, Srivastava, Krizhevsky, Sutskever and Salakhutdinov showed that using dropout in a feed-forward neural network improved performance significantly. In particular they produced this result for the MNIST dataset: However, if you try to create this result in PyTorch using modern standards …
ALL YOUR BASE ARE BELONG TO US
Physics. Data Science. General Geekery. Probably Coffee.
ALL YOUR BASE ARE BELONG TO US 