Lectures
Note that each lecture will be released weekly after each class.
-
Lecture 1: Introduction to AI, Intelligent Agents
tl;dr: This lecture makes an introduction to AI and reviews scope of the course -
Lecture 2: Uninformed Search: Depth-first, Breadth-first, and Uniform Cost Search
tl;dr: This lecture is about search algorithms that generate the search tree without using domain specific knowledge -
Lecture 3: Informed Search: A* Search, Heuristics, and Adversarial Search
tl;dr: This lecture is about search algorithms that use problem-specific knowledge beyond the problem definition -
Lecture 4: Constraint Satisfaction Problems
tl;dr: This lecture is about the formulation of Constraint Satisfaction Problems and algorithms for solving them -
Lecture 5: Game Trees: Minimax, Expectimax, Utilities
tl;dr: This lecture is about algorithms used in games to find the best moves -
Lecture 6: Markov Decision Processes
tl;dr: This lecture is about mathematical framework for modeling decision making where outcomes are partly random -
Lecture 7: Reinforcement Learning
tl;dr: This lecture is about how agents ought to take actions in an environment so as to maximize expected reward -
Lecture 8: Bayes’ Nets: Representation, Independence, Inference, and Sampling
tl;dr: This lecture is about a type of probabilistic graphical models efficient for reasonning over many variables -
Lecture 9: Decision Networks
tl;dr: This lecture is about graphical models that extend belief networks to include decision variables and utility -
Lecture 10: Hidden Markov Models
tl;dr: This lecture is about models in which the system is assumed to be a Markov process with unobservable states -
Lecture 11*: Learning: Naïve Bayes
tl;dr: This lecture is about simple classifiers based on Bayes Nets with (naive) independence assumptions between features -
Lecture 12*: Learning: Perceptrons and Logistic Regression
tl;dr: This lecture is about simple models and algorithms for supervised learning of binary and multi-class classifiers -
Lecture 13*: Learning: Optimization and Deep Neural Networks
tl;dr: This lecture is about optimization techniques to train models and build deep nerual networks from multi-class logistic regression models -
Lecture 14*: Learning: Learning Theory and Decision Trees
tl;dr: This lecture is about studying the design and analysis of machine learning algorithms -
Lecture 15*: Advanced Applications: Robotics and Beyond
tl;dr: This lecture is about recent applications of AI and machine learning in our today's society -
Guest Lecture (Mohammad Ali Javidian): Structure Learning in Bayesian Networks: The PC Algorithm
tl;dr: This guest lecture is about a constraint-based structure learning in Bayes’ Nets