Auto-Encoding Variational Bayes
GPTKB entity
Statements (108)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:television_channel
gptkb:software_framework |
| gptkbp:bfsLayer |
4
|
| gptkbp:bfsParent |
gptkb:Hugo_Larochelle
gptkb:Ilya_Sutskever gptkb:D._P._Kingma |
| gptkbp:allows |
requires large datasets
sensitive to hyperparameters may converge to local optima |
| gptkbp:applies_to |
gptkb:robot
computer vision financial modeling natural language processing probabilistic modeling probabilistic graphical models |
| gptkbp:based_on |
Bayes' theorem
|
| gptkbp:can_be_used_with |
autoencoders and variational inference
|
| gptkbp:developed_by |
gptkb:D._P._Kingma
gptkb:M._Welling high-dimensional data D. P. Kingma and M. Welling researchers in machine learning |
| gptkbp:enables |
efficient inference
|
| gptkbp:has_impact_on |
unsupervised learning
|
| gptkbp:has_programs |
computer vision
natural language processing generative modeling |
| gptkbp:has_variants |
gptkb:Conditional_Variational_Autoencoder
Discrete Variational Autoencoder Hierarchical Variational Autoencoder |
| https://www.w3.org/2000/01/rdf-schema#label |
Auto-Encoding Variational Bayes
|
| gptkbp:improves |
latent variable models
generative models |
| gptkbp:introduced |
gptkb:D._P._Kingma
|
| gptkbp:is_adopted_by |
research institutions
startups industry applications |
| gptkbp:is_challenged_by |
overfitting
computational complexity mode collapse |
| gptkbp:is_cited_in |
gptkb:academic_journal
research articles machine learning textbooks many subsequent studies deep learning literature over 500 papers |
| gptkbp:is_considered_as |
state-of-the-art method
generative adversarial networks alternative |
| gptkbp:is_evaluated_by |
cross-validation
posterior predictive checks likelihood estimation |
| gptkbp:is_explored_in |
gptkb:academic_conferences
research papers workshops conferences numerous research papers theses research collaborations thesis works |
| gptkbp:is_implemented_in |
gptkb:Graphics_Processing_Unit
gptkb:Py_Torch |
| gptkbp:is_influenced_by |
gptkb:television_channel
variational methods autoencoders variational autoencoders deep generative models |
| gptkbp:is_part_of |
gptkb:Artificial_Intelligence
gptkb:software_framework AI applications machine learning frameworks data science methodologies AI research community statistical learning theory Bayesian deep learning |
| gptkbp:is_promoted_by |
tutorials
workshops online courses |
| gptkbp:is_related_to |
gptkb:computer
gptkb:Bayesian_neural_networks gptkb:Markov_Chain_Monte_Carlo Bayesian inference deep learning information theory variational methods probabilistic modeling latent space representation variational autoencoder |
| gptkbp:is_supported_by |
stochastic gradient descent
reparameterization trick variational lower bounds |
| gptkbp:is_used_for |
text generation
data generation feature learning data imputation |
| gptkbp:is_used_in |
time series analysis
speech recognition text generation anomaly detection image generation |
| gptkbp:is_utilized_in |
reinforcement learning
social network analysis healthcare analytics |
| gptkbp:provides |
approximate posterior inference
|
| gptkbp:published_by |
gptkb:2013
|
| gptkbp:related_to |
latent variable models
variational inference |
| gptkbp:uses |
gptkb:microprocessor
variational inference |