|
gptkbp:instanceOf
|
gptkb:artificial_intelligence
deep generative model
|
|
gptkbp:application
|
image generation
semi-supervised learning
representation learning
anomaly detection
data denoising
|
|
gptkbp:basedOn
|
variational Bayesian methods
autoencoder architecture
|
|
gptkbp:citation
|
gptkb:Auto-Encoding_Variational_Bayes
|
|
gptkbp:consistsOf
|
decoder
encoder
|
|
gptkbp:field
|
gptkb:artificial_intelligence
gptkb:machine_learning
computer vision
probabilistic modeling
|
|
gptkbp:hasVariant
|
gptkb:beta-VAE
gptkb:disentangled_VAE
conditional variational autoencoder
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Variational autoencoder
|
|
gptkbp:introduced
|
gptkb:Diederik_P._Kingma
gptkb:Max_Welling
|
|
gptkbp:introducedIn
|
2013
|
|
gptkbp:latentSpace
|
continuous
|
|
gptkbp:learns
|
latent variable model
|
|
gptkbp:lossFunction
|
gptkb:Kullback-Leibler_divergence
reconstruction loss
|
|
gptkbp:objective
|
ELBO
evidence lower bound
|
|
gptkbp:publishedIn
|
arXiv:1312.6114
|
|
gptkbp:relatedTo
|
gptkb:convolutional_neural_network
Bayesian inference
|
|
gptkbp:trainer
|
stochastic gradient descent
|
|
gptkbp:usedFor
|
data compression
dimensionality reduction
unsupervised learning
generative modeling
|
|
gptkbp:uses
|
reparameterization trick
|
|
gptkbp:bfsParent
|
gptkb:Boltzmann_machine
|
|
gptkbp:bfsLayer
|
5
|