Generative Models Based on VAE and GAN for New Medical Data Synthesis: Chap.; Society 5.0: Cyberspace for Advanced Human-Centered Society; Vol. 333 : Studies in Systems, Decision and Control (SSDC)
| Parent link: | Society 5.0: Cyberspace for Advanced Human-Centered Society/ eds. A. G. Kravets, A. A. Bolshakov, M. Shcherbakov Vol. 333 : Studies in Systems, Decision and Control (SSDC).— 2021.— [P. 217-226] |
|---|---|
| Autor principal: | |
| Corporate Authors: | , |
| Outros Autores: | , |
| Resumo: | Title screen The chapter deals with the construction of generative models using Variational Autoencoder (VAE) and Generative Adversarial Neural Networks to synthesize new medical data. VAE is a synthesis of two complete neural networks: an encoder E and a generator G, as well as the latent space connecting them and enabling them to carry out random transformation and interpolation. Generative Adversarial Nets (GAN) in their turn are built on the principle of interaction between a generative model (generator G) and a discriminating model (discriminator D). When creating generator G (both VAE and GAN), its architecture of a neural network based on convolutional layers, with the application of the new deep learning framework Tensorflow-addons is used. As E and D encoders, respectively, the models of transfer learning, problem domain-image feature vector are used in the work. The comparison between them is made in the chapter and the most optimal model for solving the proposed problem is selected. The chapter presents the results of the research obtained on the basis of VAE and GAN implementation. Режим доступа: по договору с организацией-держателем ресурса |
| Idioma: | inglês |
| Publicado em: |
2021
|
| Assuntos: | |
| Acesso em linha: | https://doi.org/10.1007/978-3-030-63563-3_17 |
| Formato: | Recurso Electrónico Capítulo de Livro |
| KOHA link: | https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=664664 |
MARC
| LEADER | 00000naa0a2200000 4500 | ||
|---|---|---|---|
| 001 | 664664 | ||
| 005 | 20260807071627.0 | ||
| 035 | |a (RuTPU)RU\TPU\network\35848 | ||
| 035 | |a RU\TPU\network\35256 | ||
| 090 | |a 664664 | ||
| 100 | |a 20210513d2021 k||y0engy50 ba | ||
| 101 | 0 | |a eng | |
| 135 | |a drcn ---uucaa | ||
| 181 | 0 | |a i | |
| 182 | 0 | |a b | |
| 200 | 1 | |a Generative Models Based on VAE and GAN for New Medical Data Synthesis |e Chap. |f V. V. Laptev, O. M. Gerget, N. A. Markova | |
| 203 | |a Text |c electronic | ||
| 300 | |a Title screen | ||
| 320 | |a [References: 8 tit.] | ||
| 330 | |a The chapter deals with the construction of generative models using Variational Autoencoder (VAE) and Generative Adversarial Neural Networks to synthesize new medical data. VAE is a synthesis of two complete neural networks: an encoder E and a generator G, as well as the latent space connecting them and enabling them to carry out random transformation and interpolation. Generative Adversarial Nets (GAN) in their turn are built on the principle of interaction between a generative model (generator G) and a discriminating model (discriminator D). When creating generator G (both VAE and GAN), its architecture of a neural network based on convolutional layers, with the application of the new deep learning framework Tensorflow-addons is used. As E and D encoders, respectively, the models of transfer learning, problem domain-image feature vector are used in the work. The comparison between them is made in the chapter and the most optimal model for solving the proposed problem is selected. The chapter presents the results of the research obtained on the basis of VAE and GAN implementation. | ||
| 333 | |a Режим доступа: по договору с организацией-держателем ресурса | ||
| 461 | |t Society 5.0: Cyberspace for Advanced Human-Centered Society |f eds. A. G. Kravets, A. A. Bolshakov, M. Shcherbakov | ||
| 463 | |t Vol. 333 : Studies in Systems, Decision and Control (SSDC) |v [P. 217-226] |d 2021 | ||
| 610 | 1 | |a электронный ресурс | |
| 610 | 1 | |a труды учёных ТПУ | |
| 610 | 1 | |a generative adversarial nets | |
| 610 | 1 | |a variational autoencoder | |
| 610 | 1 | |a convolution neural network | |
| 610 | 1 | |a generation | |
| 610 | 1 | |a transfer learning | |
| 610 | 1 | |a discrimination | |
| 610 | 1 | |a distribution | |
| 610 | 1 | |a probability | |
| 610 | 1 | |a training | |
| 610 | 1 | |a автоэнкодеры | |
| 610 | 1 | |a сверточные нейронные сети | |
| 610 | 1 | |a дискриминация | |
| 610 | 1 | |a вероятности | |
| 700 | 1 | |a Laptev |b V. V. |g Vladislav Vitaljevich | |
| 701 | 1 | |a Gerget |b O. M. |c Specialist in the field of informatics and computer technology |c Professor of Tomsk Polytechnic University, Doctor of Sciences |f 1974- |g Olga Mikhailovna |3 (RuTPU)RU\TPU\pers\31430 |9 15593 | |
| 701 | 1 | |a Markova |b N. A. |c linguist |c Lecturer of Tomsk Polytechnic University |f 1976- |g Natalia Aleksandrovna |3 (RuTPU)RU\TPU\pers\32853 |9 16701 | |
| 712 | 0 | 2 | |a Национальный исследовательский Томский политехнический университет |b Инженерная школа информационных технологий и робототехники |c 2017- |x TPU |7 ca |8 rus |9 28330 |
| 712 | 0 | 2 | |a Национальный исследовательский Томский политехнический университет |b Школа базовой инженерной подготовки |c (2017- ) |h 8028 |9 28325 |
| 801 | 2 | |a RU |b 63413507 |c 20210910 |g RCR | |
| 856 | 4 | |u https://doi.org/10.1007/978-3-030-63563-3_17 | |
| 942 | |c CF | ||