CS6300

This course introduces modern probabilistic approaches towards creating intelligent systems, where rationale decision-making is phrased in terms of maximizing expected utility. Basic concepts of search are introduced, leading to search under uncertainty, Markov decision processes, Bellman's equations, and reinforcement learning, Bayes nets are introduced to reduce dependencies among variables. Hidden Markov models and partially observable Markov decision processes are introduced to handle uncertainties in state.

Prerequisites: CS 3505 AND CS 3130 AND CS 4150.

Fall and Spring