Statements (54)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:model
generative model |
| gptkbp:application |
data compression
image generation representation learning anomaly detection |
| gptkbp:canBe |
dimensionality reduction
feature extraction semi-supervised learning data synthesis data denoising generating new samples missing data imputation |
| gptkbp:category |
gptkb:model
unsupervised learning algorithm deep generative model |
| gptkbp:citation |
gptkb:Kingma,_D.P._&_Welling,_M._(2013)._Auto-Encoding_Variational_Bayes.
arXiv:1312.6114 |
| gptkbp:field |
gptkb:artificial_intelligence
deep learning unsupervised learning |
| gptkbp:hasComponent |
latent space
decoder encoder |
| gptkbp:hasConcept |
variational inference
probabilistic modeling reparameterization trick encoder-decoder architecture latent variable model |
| gptkbp:hasVariant |
gptkb:beta-VAE
gptkb:disentangled_VAE conditional variational autoencoder |
| https://www.w3.org/2000/01/rdf-schema#label |
variational autoencoders
|
| gptkbp:input |
data sample
|
| gptkbp:introduced |
gptkb:Diederik_P._Kingma
gptkb:Max_Welling |
| gptkbp:introducedIn |
2013
|
| gptkbp:lossFunction |
reconstruction loss
KL divergence loss |
| gptkbp:objective |
gptkb:Kullback-Leibler_divergence
evidence lower bound |
| gptkbp:openSource |
gptkb:TensorFlow
gptkb:Keras gptkb:PyTorch |
| gptkbp:output |
gptkb:organization
latent representation |
| gptkbp:relatedTo |
gptkb:generative_adversarial_networks
Bayesian inference autoencoders |
| gptkbp:uses |
neural networks
stochastic gradient descent |
| gptkbp:bfsParent |
gptkb:GANs
gptkb:Deep_energy-based_models |
| gptkbp:bfsLayer |
6
|