Generative Models Based on VAE and GAN for New Medical Data Synthesis Chap.

Generative Models Based on VAE and GAN for New Medical Data Synthesis, Chap.

Podrobná bibliografie
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]
Hlavní autor: Laptev V. V. Vladislav Vitaljevich
Korporace: Национальный исследовательский Томский политехнический университет Инженерная школа информационных технологий и робототехники Отделение информационных технологий, Национальный исследовательский Томский политехнический университет Школа базовой инженерной подготовки Отделение иностранных языков
Další autoři: Gerget O. M. Olga Mikhailovna, Markova N. A. Natalia Aleksandrovna
Shrnutí: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
Vydáno: 2021
Témata:
электронный ресурс
труды учёных ТПУ
generative adversarial nets
variational autoencoder
convolution neural network
generation
transfer learning
discrimination
distribution
probability
training
автоэнкодеры
сверточные нейронные сети
дискриминация
вероятности
On-line přístup:https://doi.org/10.1007/978-3-030-63563-3_17
Médium: Elektronický zdroj Kapitola
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=664664

Podobné jednotky

Podobné jednotky