Artificial Intelligence

No other field in computer science has higher visibility (and expectation, and disappointment) than artificial intelligence to the general population.  This course covers the basic components of artificial intelligence as we know it, namely search, optimization, logic and machine learning.   You should be able to build simple but interesting AI systems at the end of the semester.

Administrative Details

Here you will find administrative information for the Winter 1396.


The required textbook for this course is:

 Artificial Intelligence: A Modern Approach (Third Edition), by Stuart J. Russell, Peter Norvig, Prentice Hall 2009 .

A supplementary textbook (recommended, but not required) is:

   Artificial Intelligence: A New Synthesis, by Nils J. Nilsson. Morgan Kaufmann 1999.

Lecture material will be drawn from both textbooks, as well as from some of the recent online AI literature.

Course Syllabus and Lecture Notes

  1. Introduction AI: history, state-of-the-art; Captcha, ESP game, Introduction (PDF)
  2. Uninformed Search DFS, BFS, iterative deepening etc. Lecture slides (Courtesy of Tomas Lozano-Perez - MIT) (PDF)
  3. Informed Search   BFS, Uniform-Cost search, Heuristic and A*  search. Lecture slides (Courtesy of Tomas Lozano-Perez - MIT) (PDF1)(PDF2), More informed search
    from Russell’s book (PPT)
  4. Constraint Satisfaction Problems (CSP)  Backtracking algorithm, Forward Checking and Constraint Propagation. Lecture slides (PDF)
  5. Beyond Classical Search Hill Climbing, Simulated Annealing (PDF), Genetic Algorithms (PDF)  
  6. Games  Adversarial Search, minimax, alpha-beta pruning. Lecture slides (PDF)
  7. Introduction to machine Learning  Basic concepts  (PDF)
  8. k-Nearest-Neighbor Algorithm (PDF)
  9. Decision Trees  Information gain (PDF), Overfitting Example (PDF)
  10. Neural Networks Perceptron (PDF)
  11. Neural Networks Multi-Layer Perceptrons(PDF)
  12. Markov Processes:  Markov Models, Hidden Markov Models(PDF)
  13. Markov Models: Applications (PDF, Courtesy of  Jan Rupnic )
  14. Markov Decision Process (PDF)
  15. Reinforcement Learning (PDF)






Course Work and Evaluation

1- Course Project 1 (Search)

2- Home Work 1 (HW)

  • Project 1: Mixture of Gaussians for Classification  and Non-linear Regression (PDF) (Data set a , JPG) (Data set b , JPG)
  • Project 2: Simple CNN for Persian font Recognition (PDF)
  • Possibly Interesting URLs

    Here is an ad hoc collection of relevant AI links and interesting tidbits. If you know of other good stuff to share with your classmates here, please let me know, and I will try to add it.