
Fall 2011, Tuesdays and Thursdays, 3:30-4:45 PM
Instructor: Svetlana Lazebnik (lazebnik -at- cs.unc.edu)
Credit: 3 units
Prerequisites: basic programming and data structures (COMP 401 and 410), algorithms (COMP 550) highly desired, basic calculus, familiarity with probability concepts a plus but not required.
Textbook: Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach, 2nd or 3rd edition.
Description: The goal of Artificial Intelligence (AI) is the design of agents that can behave rationally in the real world by sensing their environment, planning their goals, and acting to maximally achieve these goals. This course provides an introductory survey to the techniques and applications of modern AI. The course will cover a broad range of conceptual approaches, from logic to probabilistic reasoning, and a broad range of applications, from natural language understanding to robotics. Lectures will stress not only the technical concepts themselves, but also the history of ideas behind them.
Grading:
| Date | Topic | Readings and assignments |
| August 23 | Intro to AI: PPT, PDF | Reading: Ch. 1 |
| August 25 | History of AI: PPT, PDF | Reading: Ch. 1 |
| August 30 | Agents: PPT, PDF | Reading: Ch. 2 |
| September 1 | Search intro: PPT, PDF | Reading: Ch. 3 |
| September 6 | Uninformed and informed search: PPT, PDF | Reading: Sec. 4.1-4.2 (2nd ed.), Ch. 3 (3rd ed.) |
| September 8 | Local search: PPT, PDF | Reading: Sec. 4.3 (2nd ed.), Sec. 4.1 (3rd ed.) Homework: Assignment 1 |
| September 13 | Constraint satisfaction problems: PPT, PDF | Reading: Ch. 5 (2nd ed.), Ch. 6 (3rd ed.) |
| September 15 | CSPs concluded; intro. to games | |
| September 20 | Adversarial search: PPT, PDF | Reading: Ch. 6 (2nd ed.), Ch. 5 (3rd ed.) |
| September 22 | Game theory: PPT, PDF | Reading: Sec. 17.6-17.7 (2nd ed.), 17.5-17.6 (3rd ed.) |
| September 27 | Game theory cont.: PPT, PDF | Assignment 1 due at 11:59PM Homework: Assignment 2 |
| September 29 | Propositional logic: PPT, PDF | Reading: Ch. 7 |
| October 4 | Guest lecture (Joe Tighe): computer vision: PPT | Reading: Ch. 24 |
| October 6 | Guest lecture (Joe Tighe): image parsing: PPT | |
| October 11 | First-order logic: PPT, PDF | Reading: Ch. 8 Practice midterm questions:DOC, PDF |
| October 13 | FOL inference: PPT, PDF Midterm review | Reading: Ch. 9 |
| October 18 | Midterm | |
| October 25 | Probability: PPT, PDF | Reading: Ch. 13 |
| October 27 | Bayesian inference: PPT, PDF | |
| November 1 | Bayesian inference cont. | Assignment 2 due at 11:59PM |
| November 3 | Bayesian networks: PPT, PDF | Reading: Ch. 14 Homework: Assignment 3 |
| November 8 | Class cancelled | |
| November 10 | Guest lecture: Ron Alterovitz | |
| November 15 | Bayesian network inference: PPT, PDF | Reading: Ch. 20 |
| November 17 | Markov decision processes: PPT, PDF | Reading: Ch. 17 Assignment 3 due at 11:59PM |
| November 22 | Reinforcement learning: PPT, PDF | Reading: Ch. 21 Homework: Assignment 4 |
| November 29 | Machine learning: PPT, PDF | Practice midterm 2 questions:DOC, PDF |
| December 1 | Conclusion: PPT, PDF Final review | |
| December 6 | Midterm 2 | Assignment 4 and extra credit due December 10 at 11:59PM -- no extensions! |