On Regularization Properties of Artificial Datasets for Deep Learning

08/19/2019
by   Karol Antczak, et al.
0

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.

READ FULL TEXT
10/31/2020

DL-Reg: A Deep Learning Regularization Technique using Linear Regression

Regularization plays a vital role in the context of deep learning by pre...
05/25/2022

Residual-Concatenate Neural Network with Deep Regularization Layers for Binary Classification

Many complex Deep Learning models are used with different variations for...
04/10/2016

Visualization Regularizers for Neural Network based Image Recognition

The success of deep neural networks is mostly due their ability to learn...
10/29/2017

Regularization for Deep Learning: A Taxonomy

Regularization is one of the crucial ingredients of deep learning, yet t...
08/24/2021

The staircase property: How hierarchical structure can guide deep learning

This paper identifies a structural property of data distributions that e...
09/06/2018

Applying Deep Learning to Derivatives Valuation

The universal approximation theorem of artificial neural networks states...
06/02/2022

Invertible Neural Networks for Graph Prediction

In this work, we address conditional generation using deep invertible ne...