Bayesian Networks, @Radboud University, 2020
Lecturer: Johannes Textor
Material:
- Lecture notes, containing strongly recommended exercises
- R companion
We are using R because it contains more software packages related to Bayesian Networks specifically.
Background reading:
- Korb & Nicholson: Bayesian Artificial Intelligence
- Pearl, Glymour & Jewell: Causal Inference in Statistics: A Primer
- Pearl & Mackenzie: The Book of Why
Components:
- Online lectures
- Weekly exercises (theoretical in lecture notes; practical ones in R companion)
- Assignment I (25%): Build a BN by hand to answer a scientific question in a real-world domain
- Assignment II (25%): Learn the structure of a BN automatically from data
- Exam (50%)
Assignments are in groups of max 3.
Lectures
- BN-1-Introduction.md
- BN-2-Bayesian_Networks_and_Prediction.md
- BN-3-Exact_Inference.md
- BN-4-Approximate_inference.md
- BN-5-Conditional_independence.md
- BN-6-Conditional_independence_II.md
- N.B. deze zou ik kunnen samenvoegen; vanaf hier lopen de lecture nummers niet meer gelijk
- BN-7-Structural_equation_models.md
- BN-8-Latent_variables.md
- BN-9-Markov_equivalence_and_structure_learning.md
- BN-10-Intervention_and_covariate_adjustment.md