Intelligent Systems II

Synopsis

1. Learning. Supervised learning with examples (e.g., decision trees and neural networks). Reinforcement learning, parameter estimation, and the distinction between MAP and ML. [4]
2. General Bayesian networks. Inference rules and likelihood estimation. [3]
3. Connection between search and logic. Theorem proving in propositional and predicate logic. Resolution and unification. [5]
4. Utility and rationality. Complex decision problems, with examples. Principle of maximum expected utility, and the Bellman equation. [3]