Bayesian Neural NetworksA Bayesian neural network is a neural network whose parameters are treated as random variables rather than fixed unknown constants.
Variational InferenceBayesian neural networks require inference over a posterior distribution:
Monte Carlo MethodsMonte Carlo methods approximate difficult mathematical quantities using random samples.
Uncertainty EstimationUncertainty estimation measures how much confidence a model should place in its own predictions.
Gaussian ProcessesA Gaussian process is a probabilistic model over functions. Instead of defining a probability distribution over parameters, as in Bayesian neural networks, a Gaussian process defines a probability distribution directly
Practical Probabilistic Modeling in PyTorchProbabilistic deep learning adds distributions to ordinary neural networks.
Summary and Further ReadingProbabilistic deep learning extends neural networks with explicit probability models.