Elements of Machine Intelligence: Probabilistic Reasoning and Graphical Models

4 credits

Bayes’ rule as a probabilistic reasoning engine; graphical models as knowledge encoders; conditional independence and D-Separation; Markov random fields; inference in graphical models; sampling methods and Markov Chain Monte Carlo (MCMC); sequential data and the Viterbi and BCJR algorithms; The Baum-Welsh algorithm for Markov Chain parameter estimation. Prerequisites: ECE 175A.