Lectures
You can download the lectures here (in PDF format). I will try to upload lectures prior to their corresponding classes.
-
Introduction to Artificial Intelligence
tl;dr: What is AI? How does it impact our lives? The current state of the art.
[slides] [notes] -
Introduction to Search
tl;dr: How to formulate intelligent behaviour as search problems?
[slides] [notes] -
Informed Search and Heuristics
tl;dr: How to perform informed search with the help of heuristics?
[slides] [notes] -
Constraint Satisfaction Problems and Iterative Improvement
tl;dr: Introduction to CSPs and how to solve them (backtracking, filtering, arc consistency, etc.); Also, iterative improvement (hill climbing, simulated annealing, genetic algorithms, etc.)
[slides] [notes] -
Game - Adversarial Search
tl;dr: What if you have an opponent? Zero-sum games, minimax, evaluation functions and alpha-beta pruning.
[slides] [notes] -
Game - Expectimax Search
tl;dr: What if the game is not fully predictable? i.e., there is stochasticity in the process.
[slides] [notes] -
Markov Decision Processes
tl;dr: How to find optimal policy in an MDP? You'll also learn about following algorithms: Value Iteration, Policy Evaluation, and Policy Iteration (all based on Bellman updated equations).
[slides] [notes] -
Reinforcement Learning
tl;dr: How to learn while playing? Reinforcement Learning, Q-learning, exploration vs. exploitation, feature-based state representation.
[slides] [notes] -
Introduction to Deep Learning*
tl;dr: What is deep learning? How is it different from machine learning? What is data representation?
[slides] [notes]