Generative adversarial network based on chaotic time series

Abstract Generative adversarial networks (GANs) are becoming increasingly important in the artificial construction of natural images and related functionalities, wherein two types of networks called generators and discriminators evolve through adversarial mechanisms. Using deep convolutional neural...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Makoto Naruse, Takashi Matsubara, Nicolas Chauvet, Kazutaka Kanno, Tianyu Yang, Atsushi Uchida
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2019
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/c3385cc93b1e4d298997877832cffd10
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c3385cc93b1e4d298997877832cffd10
record_format	dspace
spelling	oai:doaj.org-article:c3385cc93b1e4d298997877832cffd102021-12-02T15:08:21ZGenerative adversarial network based on chaotic time series10.1038/s41598-019-49397-22045-2322https://doaj.org/article/c3385cc93b1e4d298997877832cffd102019-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-019-49397-2https://doaj.org/toc/2045-2322Abstract Generative adversarial networks (GANs) are becoming increasingly important in the artificial construction of natural images and related functionalities, wherein two types of networks called generators and discriminators evolve through adversarial mechanisms. Using deep convolutional neural networks and related techniques, high-resolution and highly realistic scenes, human faces, etc. have been generated. GANs generally require large amounts of genuine training data sets, as well as vast amounts of pseudorandom numbers. In this study, we utilized chaotic time series generated experimentally by semiconductor lasers for the latent variables of a GAN, whereby the inherent nature of chaos could be reflected or transformed into the generated output data. We show that the similarity in proximity, which describes the robustness of the generated images with respect to minute changes in the input latent variables, is enhanced, while the versatility overall is not severely degraded. Furthermore, we demonstrate that the surrogate chaos time series eliminates the signature of the generated images that is originally observed corresponding to the negative autocorrelation inherent in the chaos sequence. We also address the effects of utilizing chaotic time series to retrieve images from the trained generator.Makoto NaruseTakashi MatsubaraNicolas ChauvetKazutaka KannoTianyu YangAtsushi UchidaNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 9, Iss 1, Pp 1-9 (2019)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Makoto Naruse Takashi Matsubara Nicolas Chauvet Kazutaka Kanno Tianyu Yang Atsushi Uchida Generative adversarial network based on chaotic time series
description	Abstract Generative adversarial networks (GANs) are becoming increasingly important in the artificial construction of natural images and related functionalities, wherein two types of networks called generators and discriminators evolve through adversarial mechanisms. Using deep convolutional neural networks and related techniques, high-resolution and highly realistic scenes, human faces, etc. have been generated. GANs generally require large amounts of genuine training data sets, as well as vast amounts of pseudorandom numbers. In this study, we utilized chaotic time series generated experimentally by semiconductor lasers for the latent variables of a GAN, whereby the inherent nature of chaos could be reflected or transformed into the generated output data. We show that the similarity in proximity, which describes the robustness of the generated images with respect to minute changes in the input latent variables, is enhanced, while the versatility overall is not severely degraded. Furthermore, we demonstrate that the surrogate chaos time series eliminates the signature of the generated images that is originally observed corresponding to the negative autocorrelation inherent in the chaos sequence. We also address the effects of utilizing chaotic time series to retrieve images from the trained generator.
format	article
author	Makoto Naruse Takashi Matsubara Nicolas Chauvet Kazutaka Kanno Tianyu Yang Atsushi Uchida
author_facet	Makoto Naruse Takashi Matsubara Nicolas Chauvet Kazutaka Kanno Tianyu Yang Atsushi Uchida
author_sort	Makoto Naruse
title	Generative adversarial network based on chaotic time series
title_short	Generative adversarial network based on chaotic time series
title_full	Generative adversarial network based on chaotic time series
title_fullStr	Generative adversarial network based on chaotic time series
title_full_unstemmed	Generative adversarial network based on chaotic time series
title_sort	generative adversarial network based on chaotic time series
publisher	Nature Portfolio
publishDate	2019
url	https://doaj.org/article/c3385cc93b1e4d298997877832cffd10
work_keys_str_mv	AT makotonaruse generativeadversarialnetworkbasedonchaotictimeseries AT takashimatsubara generativeadversarialnetworkbasedonchaotictimeseries AT nicolaschauvet generativeadversarialnetworkbasedonchaotictimeseries AT kazutakakanno generativeadversarialnetworkbasedonchaotictimeseries AT tianyuyang generativeadversarialnetworkbasedonchaotictimeseries AT atsushiuchida generativeadversarialnetworkbasedonchaotictimeseries
_version_	1718388211397427200

Generative adversarial network based on chaotic time series

Ejemplares similares