A Sober Look at Neural Network Initializations
Machine Learning
2019-09-06 v2 Machine Learning
Abstract
Initializing the weights and the biases is a key part of the training process of a neural network. Unlike the subsequent optimization phase, however, the initialization phase has gained only limited attention in the literature. In this paper we discuss some consequences of commonly used initialization strategies for vanilla DNNs with ReLU activations. Based on these insights we then develop an alternative initialization strategy. Finally, we present some large scale experiments assessing the quality of the new initialization strategy.
Cite
@article{arxiv.1903.11482,
title = {A Sober Look at Neural Network Initializations},
author = {Ingo Steinwart},
journal= {arXiv preprint arXiv:1903.11482},
year = {2019}
}