Bibliography (6):
Rip van Winkle’s Razor: A Simple Estimate of Overfit to Test Data
Deep Residual Learning for Image Recognition
ImageNet Large Scale Visual Recognition Challenge
DenseNet: Densely Connected Convolutional Networks
Wikipedia Bibliography:
Minimum description length
https://en.wikipedia.org/wiki/Batch-Norm :
https://en.wikipedia.org/wiki/Batch-Norm