Bayesian learning for neural networks

E1031257
Bayesian method machine learning method neural network training approach probabilistic modeling technique

Bayesian learning for neural networks is an approach that applies Bayesian inference to neural network models, treating their weights as probability distributions to improve uncertainty estimation and generalization.

Jump to: Surface forms Statements Referenced by

Observed surface forms (2)

Surface form Occurrences
Bayesian Learning for Neural Networks 3
Bayesian methods for neural networks 1

Statements (48)

Predicate Object
instanceOf Bayesian method ⓘ
machine learning method ⓘ
neural network training approach ⓘ
probabilistic modeling technique ⓘ
aimsAt improving generalization ⓘ
improving uncertainty estimation ⓘ
appliesTo neural networks ⓘ
assumes likelihood model for data given weights ⓘ
benefits out-of-distribution detection ⓘ
small-data regimes ⓘ
canUse dropout as approximate Bayesian inference ⓘ
ensembles as approximate Bayesian methods ⓘ
computes posterior over weights given data ⓘ
contrastsWith empirical risk minimization with deterministic weights ⓘ
maximum likelihood training of neural networks ⓘ
point-estimate training of neural networks ⓘ
enables better decision making under uncertainty ⓘ
calibrated predictive probabilities ⓘ
principled uncertainty quantification ⓘ
facesChallenge computational complexity ⓘ
intractable exact posteriors ⓘ
helpsWith model selection ⓘ
overfitting control ⓘ
regularization of neural networks ⓘ
isUsedIn Bayesian optimization NERFINISHED ⓘ
active learning ⓘ
reinforcement learning ⓘ
safety-critical applications ⓘ
uncertainty-aware prediction ⓘ
models parameter uncertainty ⓘ
predictive uncertainty ⓘ
oftenUses Bayesian model averaging NERFINISHED ⓘ
Laplace approximation NERFINISHED ⓘ
Markov chain Monte Carlo NERFINISHED ⓘ
Monte Carlo sampling ⓘ
expectation propagation NERFINISHED ⓘ
variational inference ⓘ
produces posterior predictive distribution ⓘ
relatedTo Bayesian neural networks NERFINISHED ⓘ
Gaussian process approximations ⓘ
probabilistic deep learning ⓘ
represents weights with probability distributions ⓘ
requires approximate inference methods ⓘ
treats network weights as random variables ⓘ
uses Bayesian inference ⓘ
usesConcept Bayes theorem NERFINISHED ⓘ
posterior distribution over weights ⓘ
prior distribution over weights ⓘ

Referenced by (5)

Full triples — surface form annotated when it differs from this entity's canonical label.

Radford M. Neal → authorOf → Bayesian learning for neural networks ⓘ
this entity surface form: Bayesian Learning for Neural Networks
Radford M. Neal → knownFor → Bayesian learning for neural networks ⓘ
Radford M. Neal → notableWork → Bayesian learning for neural networks ⓘ
this entity surface form: Bayesian Learning for Neural Networks
Radford M. Neal → thesisSubject → Bayesian learning for neural networks ⓘ
this entity surface form: Bayesian methods for neural networks
Radford M. Neal → thesisTitle → Bayesian learning for neural networks ⓘ
this entity surface form: Bayesian Learning for Neural Networks