Modeling and Reasoning with Bayesian Networks

　　A thorough introduction to the formal foundations andpractical applications of Bayesian networks. It provides anextensive discussion of techniques for building Bayesian networksthat model real-world situations, including techniques forsynthesizing models from design, learning models from data, anddebugging models using sensitivity analysis. It also treats exactand approximate inference algorithms at both theoretical andpractical levels. The treatment of exact algorithms covers the maininference paradigms based on elimination and conditioning andincludes advanced methods for compiling Bayesian networks,time-space tradeoffs, and exploiting local structure of massivelyconnected networks. The treatment of approximate algorithms coversthe main inference paradigms based on sampling and optimization andincludes influential algorithms such as importance sampling, MCMC,and belief propagation. The author assumes very little backgroundon the covered subjects, supplying in-depth discussions fortheoretically inclined readers and enough practical details toprovide an algorithmic cookbook for the system developer.