Posterior Inference on Infinitely Wide Bayesian Neural Networks under Weights with Unbounded Variance.
Jorge LoríaAnindya BhadraPublished in: CoRR (2023)
Keyphrases
- neural network
- posterior distribution
- markov chain monte carlo
- posterior probability
- bayesian inference
- bayesian model
- bayesian networks
- variational inference
- bayesian model selection
- bayesian learning
- pattern recognition
- probability distribution
- fuzzy logic
- bayesian models
- bayesian framework
- probabilistic model
- markov chain monte carlo methods
- linear combination
- weighted sum
- probabilistic inference
- parameter estimation
- hidden neurons
- weight update
- artificial neural networks
- neural nets
- genetic algorithm
- latent variables
- fault diagnosis
- gaussian process
- neural network model
- self organizing maps
- prior probabilities
- inference process
- model averaging
- back propagation
- dirichlet process
- maximum likelihood
- wide range
- multilayer perceptron
- prior knowledge
- graphical models
- particle filter
- loopy belief propagation
- finite number
- correlation coefficient
- hyperparameters