CSE 4633/6633 Introduction to Artificial Intelligence (Fall 2017) - Course Schedule 




Thu 8/17 Course overview and introduction. Read recent NY Times article on recent advances in AI
Tues 8/22 Introduction to state-space search and uninformed search algorithms: breadth-first, uniform-cost, depth-first, and iterative-deepening search
Example: Cannibals and missionaries problem
Read R&N textbook, chapter 3
Thu 8/24 Introduction to informed (heuristic) search algorithms: A*, IDA*, admissible and consistent heuristics
Example: Sliding-tile puzzle
Helpful links for implementing A*: 0, 1, 2, 3
Tues 8/29 Informed search algorithms continued: Branch-and-bound search
Example: Traveling salesman problem
Brief review of depth-first branch-and-bound search
Thu 8/31 Constraint-satisfaction problems: backtracking search with constraint propagation
Examples: Sudoku, N-queens, many others
Read R&N textbook, chapter 6
Helpful links for implementing backtracking with constraint propagation: 0, 1
Tues 9/5 Adversarial and game-tree search
Examples: Chess, checkers
Read R&N textbook, chapter 5
Thu 9/7 Quiz and review

Tues 9/12 Local search, hill climbing, and related incomplete search algorithms
Read R&N textbook, sections 4.1 and 6.4
Local search for the traveling salesman problem
Thu 9/14 Introduction to machine learning and neural networks
1st programming assignment due
Tues 9/19 Backpropagation algorithm for training feedforward multi-layer neural networks Read R&N textbook, section 18.7
Some helpful links for backpropagation: 1, 2, 3, 4, 5
Thu 9/21 Learning decision trees Read R&N textbook, sections 18.1 through 18.4
Tues 9/27 Naive Bayes classifiers
Readings on Naive Bayes classifiers: 1, 2
Thu 9/29 Unsupervised learning and k-means clustering

Tues 10/3 Review for midterm
Tues 10/10 Review for midterm
2nd programming assignment due
Thu 10/12 Midterm

Tues 10/17 Markov decision processes: value iteration and policy iteration Read R&N textbook, section 17.1, 17.2, 17.3
Thu 10/19 Reinforcement learning: Q-learning Read R&N textbook, chapter 21
Tues 10/24 Reinforcement learning continued: SARSA learning

Thu 10/26 Generalization in machine learning: bias-variance tradeoff

Tues 10/31 Nearest neighbors classifiers

Tues 11/7
3rd programming assignment due
Thu 11/9

Tues 11/14

Thu 11/16

Tues 11/21

Tues 11/28

Mon 12/4 Final exam 12 - 3