Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks

by   Guangyong Chen, et al.

In this work, we propose a novel technique to boost training efficiency of a neural network. Our work is based on an excellent idea that whitening the inputs of neural networks can achieve a fast convergence speed. Given the well-known fact that independent components must be whitened, we introduce a novel Independent-Component (IC) layer before each weight layer, whose inputs would be made more independent. However, determining independent components is a computationally intensive task. To overcome this challenge, we propose to implement an IC layer by combining two popular techniques, Batch Normalization and Dropout, in a new manner that we can rigorously prove that Dropout can quadratically reduce the mutual information and linearly reduce the correlation between any pair of neurons with respect to the dropout layer parameter p. As demonstrated experimentally, the IC layer consistently outperforms the baseline approaches with more stable training process, faster convergence speed and better convergence limit on CIFAR10/100 and ILSVRC2012 datasets. The implementation of our IC layer makes us rethink the common practices in the design of neural networks. For example, we should not place Batch Normalization before ReLU since the non-negative responses of ReLU will make the weight layer updated in a suboptimal way, and we can achieve better performance by combining Batch Normalization and Dropout together as an IC layer.


page 1

page 2

page 3

page 4


Optimization Theory for ReLU Neural Networks Trained with Normalization Layers

The success of deep neural networks is in part due to the use of normali...

Adjusting for Dropout Variance in Batch Normalization and Weight Initialization

We show how to adjust for the variance introduced by dropout with correc...

Training Deep Neural Networks Without Batch Normalization

Training neural networks is an optimization problem, and finding a decen...

Non-Proportional Parametrizations for Stable Hypernetwork Learning

Hypernetworks are neural networks that generate the parameters of anothe...

Improved Dropout for Shallow and Deep Learning

Dropout has been witnessed with great success in training deep neural ne...

Ensemble Model Patching: A Parameter-Efficient Variational Bayesian Neural Network

Two main obstacles preventing the widespread adoption of variational Bay...

On the Convergence of Shallow Neural Network Training with Randomly Masked Neurons

Given a dense shallow neural network, we focus on iteratively creating, ...

Please sign up or login with your details

Forgot password? Click here to reset