Add support for Conformal(ized) Bayes to ConformalPrediction.jl

ConformalPrediction.jl is a package for Predictive Uncertainty Quantification through Conformal Prediction for Machine Learning models trained in MLJ. This project aims to enhance ConformalPrediction.jl by adding support for the Conformal(ized) Bayes technique. The conformalized Bayes technique integrates conformal prediction with Bayesian inference to create prediction intervals that have the desired frequentist coverage properties while still being informed by the Bayesian posterior distribution. The integration will be carried out while maintaining consistency with the existing codebase, ensuring seamless incorporation of new functionalities. In addition to this primary objective, new methods for assessing the quality of probabilistic estimates and new recalibration method will be integrated into LaplaceRedux.jl, which is a library written in pure Julia that can be used for effortless Bayesian Deep Learning through Laplace Approximation (LA).