Post grad course on Probabilistic Reasoning April 12-15
Tue 12.4. 9 - 11
Wed 13.4. 12 - 14
Thu 14.4. 12 -14
Fri 15.4. 12 -14
Abstract: One of the primary goals of AI is the design, control and analysis of agents or systems that behave appropriately in various circumstances. In real world, the agents usually work withing complex stochastic systems and/or have incomplete information about the system. Good decision making requires that the agent have knowledge or beliefs about its environment and its dynamics, about its own abilities to observe and change the environment, and about its own goals and preferences. In this course we will examine some of the techniques for modeling decision problems of various types and the computational methods used to solve them. We will focus mainly on probabilistic models of reasoning, and on sequential decision making. The course will cover both the theoretical basis of decision making under uncertainty, and the practical applications of these algorithms.
Content: Probability Theory and Uncertainty Probabilistic Reasoning and Bayesian Networks Probabilistic Reasoning over Time Dynamic Bayesian Networks Making Simple Decisions Making Complex Decisions
Literature: Stuart Russell and Peter Norvig. Artificial Intelligence: A Modern Approach. Prentice Hall, 2002. Finn V. Jensen. Bayesian Networks and Decision Graphs. Springer-Verlag. 2001. Judea Pearl. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann. 1988 Richard S. Sutton, Andrew G. Barto. Reinforcement Learning: An Introduction. MIT Press. 1998.
Credits: will be discussed at the first lecture
Registration to firstname.lastname@example.org by Apr 11.