Results 11 to 20 of about 116,908 (254)
Generative adversarial networks [PDF]
Communications of the ACM, 2020 Generative adversarial networks are a kind of artificial intelligence algorithm designed to solve the generative modeling problem. The goal of a generative model is to study a collection of training examples and learn the probability distribution that generated them.
Goodfellow, Ian J. +7 more
openaire +4 more sources
Generative Adversarial Networks [PDF]
International Conference on Computer Vision and Pattern Analysis (ICCPA 2021), 2022 Seyedeh Leili Mirtaheri, Reza Shahbazian
exaly +7 more sources
Generating mobility networks with generative adversarial networks
EPJ Data Science, 2022 The increasingly crucial role of human displacements in complex societal phenomena, such as traffic congestion, segregation, and the diffusion of epidemics, is attracting the interest of scientists from several disciplines.
Giovanni Mauro +4 more
doaj +5 more sources
Steganographic Generative Adversarial Networks [PDF]
Twelfth International Conference on Machine Vision (ICMV 2019), 2019 Steganography is collection of methods to hide secret information ("payload") within non-secret information "container"). Its counterpart, Steganalysis, is the practice of determining if a message contains a hidden payload, and recovering it if possible.
Burnaev, Evgeny +2 more
core +2 more sources
Generative Adversarial Networks: An Overview [PDF]
IEEE Signal Processing Magazine, 2018 Generative adversarial networks (GANs) provide a way to learn deep representations without extensively annotated training data. They achieve this through deriving backpropagation signals through a competitive process involving a pair of networks. The representations that can be learned by GANs may be used in a variety of applications, including image ...
Antonia Creswell +5 more
openaire +6 more sources
Generative Adversarial Networks
2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT), 2023 Generative adversarial networks (GANs) have transformed machine learning and created new research and application areas. GANs are now used for data augmentation, picture, audio, text-to-image, and 3D object production thanks to IoT. These applications could make IoT devices more personalized, efficient, and productive by collecting and using data. GANs
Branka Hadji Misheva, Joerg Osterrieder
+8 more sources
Triple Generative Adversarial Networks [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022 We propose a unified game-theoretical framework to perform classification and conditional image generation given limited supervision. It is formulated as a three-player minimax game consisting of a generator, a classifier and a discriminator, and therefore is referred to as Triple Generative Adversarial Network (Triple-GAN).
Chongxuan Li +4 more
openaire +3 more sources
Hamiltonian quantum generative adversarial networks
Physical Review ResearchWe propose Hamiltonian quantum generative adversarial networks (HQuGANs) to learn to generate unknown input quantum states using two competing quantum optimal controls. The game-theoretic framework of the algorithm is inspired by the success of classical
Leeseok Kim, Seth Lloyd, Milad Marvian
doaj +3 more sources
Quaternion Generative Adversarial Networks [PDF]
, 2022 Accepted as a Chapter for the SPRINGER book "Generative Adversarial Learning: Architectures and Applications"
Grassucci, Eleonora +2 more
openaire +3 more sources
Generative Adversarial Networks
International Journal for Research in Applied Science and Engineering Technology, 2021 Abstract: Deep learning's breakthrough in the field of artificial intelligence has resulted in the creation of a slew of deep learning models. One of these is the Generative Adversarial Network, which has only recently emerged. The goal of GAN is to use unsupervised learning to analyse the distribution of data and create more accurate results.
+5 more sources