Ramifications of Approximate Posterior Inference for Bayesian Deep Learning in Adversarial and Out-of-Distribution Settings.
John MitrosArjun PakrashiBrian Mac NameePublished in: ECCV Workshops (1) (2020)
Keyphrases
- deep learning
- probability distribution
- posterior distribution
- posterior probability
- bayesian networks
- markov chain monte carlo
- bayesian inference
- unsupervised learning
- unsupervised feature learning
- machine learning
- probabilistic model
- weakly supervised
- maximum likelihood
- computer vision
- mental models
- gaussian process
- parameter estimation
- latent variables
- bayesian framework
- expectation maximization
- higher order
- input image