Information
-
Instructor: Amarda
Shehu amarda\AT\gmu.edu
TA: Patel Rajesh rpatel17\AT\gmu.edu
Class Place and Time: Innovation Hall 136, W 4:30-7:10 pm
TA Office Hours: ENGR 5321, W 2:30-4:30 pm
Instructor Office Hours: ENGR #4452, M 2:30-4:30 pm
- Lectures incorporate and adapt material from instructors primarily from UC Berkeley and George Mason University, such as Stuart Russell, Pieter Abeel, Gheorghe Tecucci, and Kenneth A De Jong.
Tentative Syllabus
| Date | Topic | Chapters | Assignments |
| Jan 24 | What is AI and Problem Solving? | Ch. 1-2 [pdf] , youtube | Breakthrough year for AI |
| Problem-Solving and Search | |||
| Jan 31 | Problem Solving and Uninformed Search | Ch. 2-3 [pdf] , youtube | Google beats human at Go |
| Feb 07 | Informed (Heuristic) Search | Ch. 3 [pdf], youtube | Hw1 Out; tutorial |
| Feb 14 | Local and Randomized Search/Optimization | Ch. 4 [pdf] | |
| Feb 21 | Game Playing (Adversarial Search) | Ch. 5 [pdf], youtube | a-b pruning demo |
| Feb 28 | Constraint Satisfaction | Ch. 6, [pdf], youtube , Freuder 90s paper | Hw1 Due, Hw2 Out |
| Knowledge and Reasoning | |||
| Mar 07 | Propositional Logic | Ch. 7 [pdf] | |
| Mar 14 | Spring Break | ||
| Mar 21 | First-order Logic | Ch. 8 [pdf] | Hw2 Due |
| Mar 28 | EXAM | Ch. 1-7 | In class, closed |
| Apr 04 | Inference in First-order Logic | Ch. 9 [pdf] | good FOL summary |
| Apr 11 | Planning: From Classic to Real-World | Ch. 10-11 [pdf] | |
| Uncertainty and Probabilistic Reasoning | |||
| Apr 18 | Bayesian Networks | Ch. 13-14 [pdf], youtube I, youtube II | Hw3 Out Home Reading Form project team |
| Apr 25 | Inference on Bayesian Networks | Ch. 14 [pdf], youtube I , youtube II | |
| Statistical Learning and Other Advanced AI Topics | |||
| May 02 | Temporal Models, Bayesian Learning, Neural Networks | Ch. 15, 18, 20 [pdf], youtube I , youtube II , youtube III , , youtube V , youtube VI | Hw3 Due White paper Due (3 pages) |
| May 09 | Final Exam | IN 136, 4:30 - 7:15 pm | (submit project code and manuscript via blackboard) |
Supplementary Step-by-step Video Lectures by Pieter Abeel/Berkeley
| DFS and BFS | Uninformed Search |
| A* Search | Informed Search |
| Alpha-Beta Pruning | Game Playing |
| D-Separation | Bayes' nets: Syntax and semantics |
| Elimination of One Variable | Bayes' nets: Exact inference |
| Variable Elimination | Bayes' nets: Exact inference |
| Sampling | Bayes' nets: Approximate inference |
| Perceptron | Machine Learning: Neural networks |
| Maximum Likelihood | Machine Learning: Statistical learning |
| Laplace Smoothing | Machine Learning: Statistical learning |