國立高雄大學圖資館 |

語系: 繁體中文

說明(常見問題)

圖資館首頁

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

BayesBiGAN and GANify: Research and ...

Dinjian, Daniel.

BayesBiGAN and GANify: Research and a Developer Tool for Generative Adversarial Networks.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	BayesBiGAN and GANify: Research and a Developer Tool for Generative Adversarial Networks.
作者:	Dinjian, Daniel.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, 2019
面頁冊數:	35 p.
附註:	Source: Masters Abstracts International, Volume: 81-04.
附註:	Advisor: Liu, Liping.
Contained By:	Masters Abstracts International81-04.
標題:	Computer science.
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=22584752
ISBN:	9781392752692

BayesBiGAN and GANify: Research and a Developer Tool for Generative Adversarial Networks.
Dinjian, Daniel.

BayesBiGAN and GANify: Research and a Developer Tool for Generative Adversarial Networks. - Ann Arbor : ProQuest Dissertations & Theses, 2019 - 35 p.

Source: Masters Abstracts International, Volume: 81-04.

Thesis (M.S.)--Tufts University, 2019.

This item must not be sold to any third party vendors.

This thesis concerns the current state of Generative Adversarial Networks (GANs) in the field of Machine Learning. The first part of the work combines the BayesGAN and the BiGAN models to create the Bayesian Bidirectional GAN (BayesBiGAN). The BayesBiGAN uses the BayesGAN’s MCMC training method to sample from posteriors over the generator, discriminator, and the BiGAN encoder. This model captures a rich underlying feature representation and encodes signals to a lower dimensional vectors. The second part of the work addresses the disconnect between GAN research and product development. GAN research is far less accessible than research in other machine learning fields due to a lack of developer tools. This drastically limits the speed and breadth of applications that can be made. This work begins to address the disconnect by creating an API that offers cloud access to CycleGAN for style transfer to convert photos into painting renderings in the style of various famous painters. The API allows developers to easily integrate the CycleGAN into their own work. An educational demo website demonstrates how the API can be used to engage a non-technical audience.

ISBN: 9781392752692Subjects--Topical Terms:

199325
Computer science.

BayesBiGAN and GANify: Research and a Developer Tool for Generative Adversarial Networks.
LDR:02204nmm a2200313 4500 001 570798
005 20200514112001.5
008 200901s2019 ||||||||||||||||| ||eng d
020 $a 9781392752692
035 $a (MiAaPQ)AAI22584752
035 $a AAI22584752
040 $a MiAaPQ $c MiAaPQ
100 1 $a Dinjian, Daniel. $3 857510
245 1 0 $a BayesBiGAN and GANify: Research and a Developer Tool for Generative Adversarial Networks.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2019
300 $a 35 p.
500 $a Source: Masters Abstracts International, Volume: 81-04.
500 $a Advisor: Liu, Liping.
502 $a Thesis (M.S.)--Tufts University, 2019.
506 $a This item must not be sold to any third party vendors.
506 $a This item must not be added to any third party search indexes.
520 $a This thesis concerns the current state of Generative Adversarial Networks (GANs) in the field of Machine Learning. The first part of the work combines the BayesGAN and the BiGAN models to create the Bayesian Bidirectional GAN (BayesBiGAN). The BayesBiGAN uses the BayesGAN’s MCMC training method to sample from posteriors over the generator, discriminator, and the BiGAN encoder. This model captures a rich underlying feature representation and encodes signals to a lower dimensional vectors. The second part of the work addresses the disconnect between GAN research and product development. GAN research is far less accessible than research in other machine learning fields due to a lack of developer tools. This drastically limits the speed and breadth of applications that can be made. This work begins to address the disconnect by creating an API that offers cloud access to CycleGAN for style transfer to convert photos into painting renderings in the style of various famous painters. The API allows developers to easily integrate the CycleGAN into their own work. An educational demo website demonstrates how the API can be used to engage a non-technical audience.
590 $a School code: 0234.
650 4 $a Computer science. $3 199325
650 4 $a Artificial intelligence. $3 194058
690 $a 0984
690 $a 0800
710 2 $a Tufts University. $b Computer Science. $3 857511
773 0 $t Masters Abstracts International $g 81-04.
790 $a 0234
791 $a M.S.
792 $a 2019
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=22584752