probly.method.bayesian

probly.method.bayesian(base: Predictor[In, Out], use_base_weights: bool = False, posterior_std: float = 0.05, prior_mean: float = 0.0, prior_std: float = 1.0) → BayesianPredictor[In, Out][source]

Create a Bayesian predictor from a base predictor based on [BCKW15].

Parameters:

  • base – The base model to be used for the Bayesian neural network.

  • use_base_weights – bool, If True, the weights of the base model are used as the prior mean.

  • posterior_std – float, The initial posterior standard deviation.

  • prior_mean – float, The prior mean.

  • prior_std – float, The prior standard deviation.

Returns:

The Bayesian predictor.