A Generative Adversarial Network Structure for Learning with Small Numerical Data Sets

Der-Chiang Li,Szu-Chou Chen,Kuan-Cheng Huang,Yao-San Lin

doi:10.3390/app112210823

Abstract

In recent years, generative adversarial networks (GANs) have been proposed to generate simulated images, and some works of literature have applied GAN to the analysis of numerical data in many fields, such as the prediction of building energy consumption and the prediction and identification of liver cancer stages. However, these studies are based on sufficient data volume. In the current era of globalization, the demand for rapid decision-making is increasing, but the data available in a short period of time is scarce. As a result, machine learning may not provide precise results. Obtaining more information from a small number of samples has become an important issue. Therefore, this study aimed to modify the generative adversarial network structure for learning with small numerical datasets, starting with the Wasserstein GAN (WGAN) as the GAN architecture, and using mega-trend-diffusion (MTD) to limit the bound of virtual samples that the GAN generates. The model verification of our proposed structure was conducted with two datasets in the UC Irvine Machine Learning Repository, and the performance was evaluated using three criteria: accuracy, standard deviation, and p-value. The experiment result shows that, using this improved GAN architecture (WGAN_MTD), small sample data can also be used to generate virtual samples that are similar to real samples through GAN.

Highlights

An increasing number of machine learning algorithms have recently moved from academia to commercial applications
We proposed a new method based on the Wasserstein generative adversarial networks (GANs) (WGAN) architecture and modified mega-trend-diffusion (MTD) as a limitation of the GAN generative network to reverse the back-propagation network (BPN) to generate and identify the networks of the GAN
This can assist in the reduction of the scope of the generated sample and saves time when the WGAN irregularly generates a virtual sample at the beginning

Summary

Introduction

An increasing number of machine learning algorithms have recently moved from academia to commercial applications. It is a very important issue to enable machine learning to undertake effective training with a small dataset. To address this issue, the main solution for the small sample problem is virtual sample generation (VSG). Generative adversarial networks (GANs) which were proposed by Goodfellow et al [13], have been a popular method of VSG. The generator is used to generate new data with a distribution similar to that of the original real data, so that the discriminator is unable to distinguish between the original and generated data, but attempts to distinguish between the two sets of data

Objectives

Methods

Results

Conclusion