001434414 000__ 03554cam\a2200589\i\4500
001434414 001__ 1434414
001434414 003__ OCoLC
001434414 005__ 20230309003728.0
001434414 006__ m\\\\\o\\d\\\\\\\\
001434414 007__ cr\un\nnnunnun
001434414 008__ 210227s2021\\\\si\\\\\\ob\\\\000\0\eng\d
001434414 019__ $$a1238005368$$a1244116345
001434414 020__ $$a9789813360488$$q(electronic book)
001434414 020__ $$a9813360488$$q(electronic book)
001434414 020__ $$z981336047X
001434414 020__ $$z9789813360471
001434414 0247_ $$a10.1007/978-981-33-6048-8$$2doi
001434414 035__ $$aSP(OCoLC)1239988140
001434414 040__ $$aEBLCP$$beng$$erda$$epn$$cEBLCP$$dGW5XE$$dOCLCO$$dYDX$$dDCT$$dOCLCF$$dUKAHL$$dOCLCQ$$dOCLCO$$dCOM$$dOCLCQ
001434414 049__ $$aISEA
001434414 050_4 $$aQ325.5
001434414 08204 $$a006.31$$223
001434414 1001_ $$aMao, Xudong,$$eauthor.
001434414 24510 $$aGenerative adversarial networks for image generation /$$cXudong Mao, Qing Li.
001434414 2463_ $$aGANs for image generation
001434414 264_1 $$aSingapore :$$bSpringer,$$c[2021]
001434414 300__ $$a1 online resource
001434414 336__ $$atext$$btxt$$2rdacontent
001434414 337__ $$acomputer$$bc$$2rdamedia
001434414 338__ $$aonline resource$$bcr$$2rdacarrier
001434414 347__ $$atext file
001434414 347__ $$bPDF
001434414 504__ $$aIncludes bibliographical references.
001434414 5050_ $$aGenerative Adversarial Networks (GANs) -- GANs for Image Generation -- More Key Applications of GANs -- Conclusions.
001434414 506__ $$aAccess limited to authorized users.
001434414 520__ $$aGenerative adversarial networks (GANs) were introduced by Ian Goodfellow and his co-authors including Yoshua Bengio in 2014, and were to referred by Yann Lecun (Facebooks AI research director) as "the most interesting idea in the last 10 years in ML." GANs potential is huge, because they can learn to mimic any distribution of data, which means they can be taught to create worlds similar to our own in any domain: images, music, speech, prose. They are robot artists in a sense, and their output is remarkable, poignant even. In 2018, Christies sold a portrait that had been generated by a GAN for $432,000. Although image generation has been challenging, GAN image generation has proved to be very successful and impressive. However, there are two remaining challenges for GAN image generation: the quality of the generated image and the training stability. This book first provides an overview of GANs, and then discusses the task of image generation and the details of GAN image generation. It also investigates a number of approaches to address the two remaining challenges for GAN image generation. Additionally, it explores three promising applications of GANs, including image-to-image translation, unsupervised domain adaptation and GANs for security. This book appeals to students and researchers who are interested in GANs, image generation and general machine learning and computer vision
001434414 588__ $$aOnline resource; title from PDF title page (SpringerLink, viewed March 19, 2021).
001434414 650_0 $$aMachine learning$$xTechnological innovations.
001434414 650_0 $$aArtificial intelligence$$xComputer programs.
001434414 650_0 $$aNeural networks (Computer science)
001434414 650_6 $$aApprentissage automatique$$xInnovations.
001434414 650_6 $$aIntelligence artificielle$$xLogiciels.
001434414 650_6 $$aRéseaux neuronaux (Informatique)
001434414 655_0 $$aElectronic books.
001434414 7001_ $$aLi, Qing,$$d1962-$$eauthor.
001434414 77608 $$iPrint version:$$z9789813360471
001434414 852__ $$bebk
001434414 85640 $$3Springer Nature$$uhttps://univsouthin.idm.oclc.org/login?url=https://link.springer.com/10.1007/978-981-33-6048-8$$zOnline Access$$91397441.1
001434414 909CO $$ooai:library.usi.edu:1434414$$pGLOBAL_SET
001434414 980__ $$aBIB
001434414 980__ $$aEBOOK
001434414 982__ $$aEbook
001434414 983__ $$aOnline
001434414 994__ $$a92$$bISE