On the Importance of Normalisation Layers in Deep Learning with Piecewise Linear Activation Units

Benchmark Model Rank Results
image-classification-on-cifar-10MIMPercentage correct: 91.5
image-classification-on-cifar-100MIMPercentage correct: 70.8
image-classification-on-mnistMIMPercentage error: 0.4
image-classification-on-svhnMIMPercentage error: 2.0