Introduction to Bayesian models and statistical analysis for machine learning.
Pre-requisite: 1st semester lectures from the M1 DS course track (Python and tools for research, Probability 1, Statistics 1, Probability 2).
Keywords: elements of Bayesian statistics (posterior, prior, conjugate priors), hierarchical Bayes models, DAG, Bayesian estimators (MMSE, MAP, MLE, type-II MLE / MAP), principle of MCMC algorithms, Metropolis-Hastings algorithm, Gibbs sampler, MALA, HCM (if time permits).
- Teacher: Pierre Antoine Thouvenin