ScholarGate
Ассистент

Сравнение методов

Просматривайте выбранные методы рядом; строки с различиями подсвечены.

Вариационный автокодировщик×Автоэнкодер×
ОбластьГлубокое обучениеГлубокое обучение
СемействоMachine learningMachine learning
Год появления20142006
Автор методаKingma, D. P. & Welling, M.Hinton, G.E. & Salakhutdinov, R.R.
ТипDeep generative latent-variable model (encoder–decoder)Neural network (encoder-decoder)
Основополагающий источникKingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR). link ↗Hinton, G.E. & Salakhutdinov, R.R. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507. DOI ↗
Другие названияDeğişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable modelOtokodlayıcı (Autoencoder), otokodlayıcı, auto-encoder, encoder-decoder network
Связанные54
СводкаThe Variational Autoencoder (VAE) is a deep generative latent-variable model, introduced by Diederik Kingma and Max Welling in 2014, that encodes data as a probability distribution in a latent space and samples from that distribution to generate new examples. It is used for data generation, anomaly detection, and feature learning.An autoencoder is an encoder-decoder neural network, popularised by Hinton and Salakhutdinov in 2006, that compresses data into a low-dimensional latent code and then reconstructs it, enabling dimensionality reduction and anomaly detection. By learning to rebuild its own input through a narrow bottleneck, it discovers a compact representation of the data.
ScholarGateНабор данных
  1. v1
  2. 2 Источники
  3. PUBLISHED
  1. v1
  2. 1 Источники
  3. PUBLISHED

Перейти к поиску Скачать слайды

ScholarGateСравнение методов: Variational Autoencoder · Autoencoder. Получено 2026-06-15 из https://scholargate.app/ru/compare