Worked solutions to all 342 exercises in Adnan Darwiche's Modeling and Reasoning with Bayesian Networks — propositional logic, probability calculus, building Bayesian networks, exact inference by variable elimination, factor elimination and conditioning, jointrees and graph decomposition, MPE and MAP, complexity, compilation, belief propagation, sampling, sensitivity analysis, and parameter/structure learning.
Bayesian-Networks
2026-09-16
A student's guide to COMP9418 at UNSW: what the course covers (Bayesian networks, exact and approximate inference, HMMs, learning), the Darwiche textbook, the open-book exam format, and free notes for every topic.
bayesian networks from first principles — the chain rule, conditional probability tables, d-separation and its valve intuition, markov blankets, i-maps, naive bayes classifiers and gaussian networks.
learning bayesian networks from data — maximum-likelihood estimation of cpts, additive smoothing, handling missing data with expectation-maximisation, and structure learning from chow-liu trees to score-based search.
the probabilistic graphical models section — bayesian and markov networks, exact and approximate inference, sequence models, and learning from data. built from unsw's comp9418.
Adnan Darwiche’s Modeling and Reasoning with Bayesian Networks (Cambridge University Press, 2009). The COMP9418 reference text: representation (propositional logic, probability calculus, Bayesian networks), exact inference (variable elimination, factor elimination, conditioning, jointrees), advanced inference (compilation, local structure), approximate inference (belief propagation, sampling), and learning (maximum likelihood and Bayesian).
Worked solutions to all 342 exercises live at Solutions to Darwiche’s Modeling and Reasoning with Bayesian Networks.