On Regularization Properties of Artificial Datasets for Deep Learning
Machine Learning
2019-08-21 v1 Machine Learning
Abstract
The paper discusses regularization properties of artificial data for deep learning. Artificial datasets allow to train neural networks in the case of a real data shortage. It is demonstrated that the artificial data generation process, described as injecting noise to high-level features, bears several similarities to existing regularization methods for deep neural networks. One can treat this property of artificial data as a kind of "deep" regularization. It is thus possible to regularize hidden layers of the network by generating the training data in a certain way.
Cite
@article{arxiv.1908.07005,
title = {On Regularization Properties of Artificial Datasets for Deep Learning},
author = {Karol Antczak},
journal= {arXiv preprint arXiv:1908.07005},
year = {2019}
}
Comments
6 pages, 1 figure