|
gptkbp:instanceOf
|
gptkb:model
generative model
|
|
gptkbp:application
|
data compression
image generation
semi-supervised learning
representation learning
anomaly detection
|
|
gptkbp:basedOn
|
gptkb:convolutional_neural_network
variational Bayesian methods
|
|
gptkbp:citation
|
Kingma, D.P. and Welling, M. (2013). Auto-Encoding Variational Bayes.
|
|
gptkbp:field
|
gptkb:artificial_intelligence
gptkb:machine_learning
computer vision
|
|
gptkbp:hasConcept
|
latent space
probabilistic decoder
probabilistic encoder
reparameterization trick
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Variational Autoencoder
|
|
gptkbp:input
|
data sample
|
|
gptkbp:introduced
|
gptkb:Diederik_P._Kingma
gptkb:Max_Welling
|
|
gptkbp:introducedIn
|
2013
|
|
gptkbp:lossFunction
|
gptkb:Kullback-Leibler_divergence
reconstruction loss
|
|
gptkbp:objective
|
evidence lower bound
|
|
gptkbp:openSource
|
gptkb:TensorFlow
gptkb:Keras
gptkb:PyTorch
|
|
gptkbp:output
|
gptkb:organization
|
|
gptkbp:relatedTo
|
gptkb:convolutional_neural_network
Boltzmann machine
Bayesian inference
|
|
gptkbp:trainer
|
backpropagation
stochastic gradient descent
|
|
gptkbp:uses
|
latent variable model
decoder network
encoder network
|
|
gptkbp:bfsParent
|
gptkb:Auto-Encoding_Variational_Bayes
gptkb:Diederik_P._Kingma
gptkb:Diederik_Kingma
gptkb:NeurIPS_2015
gptkb:Stable_Diffusion_model
|
|
gptkbp:bfsLayer
|
6
|