The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective.
Geoff PleissJohn P. CunninghamPublished in: NeurIPS (2021)
Keyphrases
- gaussian process
- neural network
- gaussian processes
- gaussian process regression
- regression model
- model selection
- bayesian framework
- expectation propagation
- approximate inference
- hyperparameters
- latent variables
- gaussian process classification
- semi supervised
- gaussian process models
- sparse approximations
- covariance function
- back propagation
- marginal likelihood
- artificial neural networks
- dynamical model
- closed form
- genetic algorithm
- bayesian methods
- pairwise
- prior knowledge
- random sampling
- cross validation
- prior information
- machine learning