Adaptive generative adversarial network (GAN) for small datasets

This paper starts from the basic mathematic knowledge in the deep learning network, then introduces some helpful and important infrastructure networks, it will also show programming tools and pods to help us build up our network. After that, this paper introduces the basic principle of GAN and analy...

Full description

Saved in:

Bibliographic Details
Main Author:	Liu, Chang
Other Authors:	Ponnuthurai Nagaratnam Suganthan
Format:	Thesis-Master by Coursework
Language:	English
Published:	Nanyang Technological University 2021
Subjects:	Engineering::Computer science and engineering::Data Engineering::Computer science and engineering::Software::Programming techniques
Online Access:	https://hdl.handle.net/10356/147096
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Nanyang Technological University
Language:	English

id	sg-ntu-dr.10356-147096
record_format	dspace
spelling	sg-ntu-dr.10356-1470962023-07-04T17:01:54Z Adaptive generative adversarial network (GAN) for small datasets Liu, Chang Ponnuthurai Nagaratnam Suganthan School of Electrical and Electronic Engineering EPNSugan@ntu.edu.sg Engineering::Computer science and engineering::Data Engineering::Computer science and engineering::Software::Programming techniques This paper starts from the basic mathematic knowledge in the deep learning network, then introduces some helpful and important infrastructure networks, it will also show programming tools and pods to help us build up our network. After that, this paper introduces the basic principle of GAN and analyzes the relevant classical GAN model. For small data sets, the method of using complex distribution such as Gaussian mixture models is proposed to enhance the simple sampling noise and a new model is created on this base which is called DeLiGAN. The main idea of the DeLiGAN is to increase the modeling capability of the prior distribution rather than increasing the depth of the model and reparametrize potential space into a mixed Gaussian model. By comparing the training results of different GAN models, it is concluded that DeLiGAN does perform better on the small data sets. This model provides a training model under a small data set, which can help us better train the neural network and improve training efficiency Master of Science (Computer Control and Automation) 2021-03-23T01:51:36Z 2021-03-23T01:51:36Z 2021 Thesis-Master by Coursework Liu, C. (2021). Adaptive generative adversarial network (GAN) for small datasets. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/147096 https://hdl.handle.net/10356/147096 en application/pdf Nanyang Technological University
institution	Nanyang Technological University
building	NTU Library
continent	Asia
country	Singapore Singapore
content_provider	NTU Library
collection	DR-NTU
language	English
topic	Engineering::Computer science and engineering::Data Engineering::Computer science and engineering::Software::Programming techniques
spellingShingle	Engineering::Computer science and engineering::Data Engineering::Computer science and engineering::Software::Programming techniques Liu, Chang Adaptive generative adversarial network (GAN) for small datasets
description	This paper starts from the basic mathematic knowledge in the deep learning network, then introduces some helpful and important infrastructure networks, it will also show programming tools and pods to help us build up our network. After that, this paper introduces the basic principle of GAN and analyzes the relevant classical GAN model. For small data sets, the method of using complex distribution such as Gaussian mixture models is proposed to enhance the simple sampling noise and a new model is created on this base which is called DeLiGAN. The main idea of the DeLiGAN is to increase the modeling capability of the prior distribution rather than increasing the depth of the model and reparametrize potential space into a mixed Gaussian model. By comparing the training results of different GAN models, it is concluded that DeLiGAN does perform better on the small data sets. This model provides a training model under a small data set, which can help us better train the neural network and improve training efficiency
author2	Ponnuthurai Nagaratnam Suganthan
author_facet	Ponnuthurai Nagaratnam Suganthan Liu, Chang
format	Thesis-Master by Coursework
author	Liu, Chang
author_sort	Liu, Chang
title	Adaptive generative adversarial network (GAN) for small datasets
title_short	Adaptive generative adversarial network (GAN) for small datasets
title_full	Adaptive generative adversarial network (GAN) for small datasets
title_fullStr	Adaptive generative adversarial network (GAN) for small datasets
title_full_unstemmed	Adaptive generative adversarial network (GAN) for small datasets
title_sort	adaptive generative adversarial network (gan) for small datasets
publisher	Nanyang Technological University
publishDate	2021
url	https://hdl.handle.net/10356/147096
_version_	1772828744078065664

Adaptive generative adversarial network (GAN) for small datasets

Similar Items