Auto-Encoding Variational Bayes
E200670
Auto-Encoding Variational Bayes is the foundational 2013 paper by Kingma and Welling that introduced variational autoencoders, a generative model framework combining deep learning with variational Bayesian inference.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Auto-Encoding Variational Bayes canonical | 5 |
How this entity was disambiguated
This entity first appeared as the object of triple T1807329 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Auto-Encoding Variational Bayes Context triple: [variational autoencoders, introducedInPaper, Auto-Encoding Variational Bayes]
-
A.
variational autoencoders
Variational autoencoders are a class of generative neural networks that learn probabilistic latent representations of data, enabling them to generate new, similar samples.
-
B.
Boltzmann machines
Boltzmann machines are stochastic recurrent neural networks used for learning complex probability distributions, foundational in unsupervised learning and energy-based models.
-
C.
“A fast learning algorithm for deep belief nets”
“A fast learning algorithm for deep belief nets” is a seminal 2006 paper by Geoffrey Hinton that introduced an efficient unsupervised pretraining method for deep neural networks using stacked restricted Boltzmann machines.
-
D.
Adam: A Method for Stochastic Optimization
"Adam: A Method for Stochastic Optimization" is a highly influential machine learning paper that introduces the Adam optimizer, a widely used adaptive gradient-based optimization algorithm for training deep neural networks.
-
E.
Generative Adversarial Networks
Generative Adversarial Networks are a class of machine learning models in which two neural networks compete to generate highly realistic synthetic data, such as images, audio, or text.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Auto-Encoding Variational Bayes Target entity description: Auto-Encoding Variational Bayes is the foundational 2013 paper by Kingma and Welling that introduced variational autoencoders, a generative model framework combining deep learning with variational Bayesian inference.
-
A.
variational autoencoders
Variational autoencoders are a class of generative neural networks that learn probabilistic latent representations of data, enabling them to generate new, similar samples.
-
B.
Boltzmann machines
Boltzmann machines are stochastic recurrent neural networks used for learning complex probability distributions, foundational in unsupervised learning and energy-based models.
-
C.
“A fast learning algorithm for deep belief nets”
“A fast learning algorithm for deep belief nets” is a seminal 2006 paper by Geoffrey Hinton that introduced an efficient unsupervised pretraining method for deep neural networks using stacked restricted Boltzmann machines.
-
D.
Adam: A Method for Stochastic Optimization
"Adam: A Method for Stochastic Optimization" is a highly influential machine learning paper that introduces the Adam optimizer, a widely used adaptive gradient-based optimization algorithm for training deep neural networks.
-
E.
Generative Adversarial Networks
Generative Adversarial Networks are a class of machine learning models in which two neural networks compete to generate highly realistic synthetic data, such as images, audio, or text.
- F. None of above. chosen
Statements (49)
| Predicate | Object |
|---|---|
| instanceOf |
deep generative model paper
ⓘ
machine learning paper ⓘ scientific paper ⓘ |
| applicationDomain |
generative modeling of images
ⓘ
semi-supervised learning ⓘ unsupervised learning ⓘ |
| approximates | intractable posterior distribution ⓘ |
| approximationFamily |
diagonal Gaussian variational posterior
ⓘ
variational distribution ⓘ |
| archive | arXiv ⓘ |
| arXivCategory |
cs.LG
ⓘ
stat.ML ⓘ |
| assumesPrior |
Gaussian prior over latent variables
ⓘ
simple prior over latent variables ⓘ |
| author |
Diederik P. Kingma
ⓘ
Max Welling ⓘ |
| citationType | highly cited paper ⓘ |
| definesAbbreviation | ELBO ⓘ |
| definesObjective | evidence lower bound ⓘ |
| field |
deep learning
ⓘ
machine learning ⓘ probabilistic modeling ⓘ variational inference ⓘ |
| influenced |
development of many VAE variants
ⓘ
research on deep generative models ⓘ |
| introducedAbbreviation |
variational autoencoders
ⓘ
surface form:
VAE
|
| introducedConcept | variational autoencoder ⓘ |
| introducesTechnique | reparameterization trick ⓘ |
| keyIdea |
combining variational Bayesian inference with deep neural networks
ⓘ
learning latent variable models with backpropagation ⓘ optimizing a variational lower bound on the log-likelihood ⓘ |
| modelType |
generative model
ⓘ
latent variable model ⓘ |
| optimizationMethod |
backpropagation
ⓘ
stochastic gradient descent ⓘ |
| proposesMethod |
auto-encoding variational Bayes framework
ⓘ
stochastic variational inference with reparameterization trick ⓘ |
| publicationStatus | preprint ⓘ |
| relatedTo |
Bayesian inference
ⓘ
autoencoders ⓘ variational Bayesian methods ⓘ |
| shortTitle | AEVB ⓘ |
| title | Auto-Encoding Variational Bayes self-link ⓘ |
| trainingCriterion | maximization of ELBO ⓘ |
| usesComponent |
decoder network
ⓘ
encoder network ⓘ generative model network ⓘ recognition model ⓘ |
| year | 2013 ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: Auto-Encoding Variational Bayes Description of subject: Auto-Encoding Variational Bayes is the foundational 2013 paper by Kingma and Welling that introduced variational autoencoders, a generative model framework combining deep learning with variational Bayesian inference.
Referenced by (5)
Full triples — surface form annotated when it differs from this entity's canonical label.