Variational autoencoder
In machine learning, a variational autoencoder (VAE), is an artificial neural network architecture introduced by Diederik P. Kingma and Max Welling, belonging to the families of probabilistic graphical models and variational Bayesian methods. Although this type of model was initially designed for unsupervised learning, its effectiveness has been proven for semi-supervised learning and supervised learning.
- Comment
- enIn machine learning, a variational autoencoder (VAE), is an artificial neural network architecture introduced by Diederik P. Kingma and Max Welling, belonging to the families of probabilistic graphical models and variational Bayesian methods. Although this type of model was initially designed for unsupervised learning, its effectiveness has been proven for semi-supervised learning and supervised learning.
- Cs1Dates
- eny
- Date
- enJune 2021
- Depiction
- Has abstract
- enIn machine learning, a variational autoencoder (VAE), is an artificial neural network architecture introduced by Diederik P. Kingma and Max Welling, belonging to the families of probabilistic graphical models and variational Bayesian methods. Variational autoencoders are often associated with the autoencoder model because of its architectural affinity, but with significant differences in the goal and mathematical formulation. Variational autoencoders are probabilistic generative models that require neural networks as only a part of their overall structure, as e.g. in VQ-VAE. The neural network components are typically referred to as the encoder and decoder for the first and second component respectively. The first neural network maps the input variable to a latent space that corresponds to the parameters of a variational distribution. In this way, the encoder can produce multiple different samples that all come from the same distribution. The decoder has the opposite function, which is to map from the latent space to the input space, in order to produce or generate data points. Both networks are typically trained together with the usage of the reparameterization trick, although the variance of the noise model can be learned separately. Although this type of model was initially designed for unsupervised learning, its effectiveness has been proven for semi-supervised learning and supervised learning.
- Is primary topic of
- Variational autoencoder
- Label
- enVariational autoencoder
- Link from a Wikipage to another Wikipage
- Artificial neural network
- Autoencoder
- Backpropagation
- Category:Bayesian statistics
- Category:Dimension reduction
- Category:Graphical models
- Category:Neural network architectures
- Category:Supervised learning
- Category:Unsupervised learning
- Chain rule (probability)
- Cholesky decomposition
- Cross entropy
- Data augmentation
- Deep learning
- Evidence lower bound
- File:Reparameterization Trick.png
- File:Reparameterized Variational Autoencoder.png
- File:VAE Basic.png
- Gaussian distribution
- Generative adversarial network
- Gradient descent
- Graphical model
- Joint distribution
- Kullback–Leibler divergence
- Machine learning
- Marginal distribution
- Max Welling
- Mean squared error
- Random number generation
- Representation learning
- Semi-supervised learning
- Sparse dictionary learning
- Stochastic gradient descent
- Supervised learning
- Unsupervised learning
- Variational Bayesian methods
- SameAs
- Auto-encodeur variationnel
- DBZzs
- Q97311562
- Variational autoencoder
- Варіаційний автокодувальник
- 変分オートエンコーダー
- Subject
- Category:Bayesian statistics
- Category:Dimension reduction
- Category:Graphical models
- Category:Neural network architectures
- Category:Supervised learning
- Category:Unsupervised learning
- Thumbnail
- WasDerivedFrom
- Variational autoencoder?oldid=1123281523&ns=0
- WikiPageLength
- 20819
- Wikipage page ID
- 62078649
- Wikipage revision ID
- 1123281523
- WikiPageUsesTemplate
- Template:Differentiable computing
- Template:Div col
- Template:Div col end
- Template:Machine learning bar
- Template:Main
- Template:Reflist
- Template:Short description
- Template:Use dmy dates
