EE570 : Artificial Intelligence

  1. Course information:
Course Title: Artificial Intelligence
Hours MW 3:00 – 4:15
Course Code: ECE595
Credits: 3 credits
Term: Fall 2016
Pre-requisite: ECE 30200 and 35900 (or graduate standing)
  1. Course Description

The course covers the application of Artificial Intelligence techniques and algorithms for problem solving. Students will learn to apply different machine learning approaches to solve real life problems related to  searching, parsing, identification, prediction, clustering, feature selection, etc…  The concepts of reasoning an inference will be discussed and used as an approach to reason about difficult problems and derive suitable algorithms for these problems.

Students are expected to discuss, critique and extend current AI research papers  as well as implement the algorithms discussed in class using their programming language of choice.

  1. Learning Objectives

Upon successful completion of the course, students should be able to

  • design and implement deterministic, heuristic and optimization algorithms
  • represent and analyse knowledge
  • use inference and reasoning to solve real-life problems
  • develop  and implement machine learning approaches
  • apply machine learning approaches to different applications and contexts.
  1. Textbook & Resources

Artificial Intelligence: A Modern Approach, Third Edition, Stuart Russell & Peter Norvig, Pearson Education Inc., December, 2009 ISBN: 978-0-13-604259-4

  1. Assessment Policy

There will be two midterms and a final exam. Students will also complete a project that will be assigned in the form of sub-projects throughout the semester.

Mid-term (2): 40 %
Project (s):  35%
Final-exam: 25 %

  1. General Classroom and Course Policies

Cheating on exams and projects will not be tolerated! Duplication and/or usage of any part of another student’s exam/homework is considered to be plagiarism. The minimum penalty assessed to a student cheating or plagiarizing (or aiding another student to do so) will be a grade of zero on the project or exam. The instructor reserves the right to administer further penalties (a failing course grade, notification of the administration, etc…).

You are to take exams on the times they are scheduled.

Projects are divided into tasks with due date as indicated below. Each task will be graded independently and must include a report and properly commented code when applicable.

  1. Course Topics

  Date Topic Reading Task
Due Date
1. 8/23 Introduction Chapter 1  
2. 8/25 Agents Chapter 2  
3. 8/30 Solving Problems by Searching (part I) Chapter 3  
4. 9/1 Solving Problems by Searching (part 2) Chapter 3 Task 1
5. 9/6 Beyond Classical Search (Informed Search) Chapter 4  
6. 9/8 Beyond Classical Search (Local Search) Chapter 4  
7. 9/13 Game Playing Chapter 5 Task 2
8. 9/15 Paper 1   presentation    
9. 9/20 Constraint Satisfaction Chapter 6  
10. 9/22 Review & QA    
11. 9/27 Midterm #1    
12. 9/29 Logical Agents (part I) Chapter 7  
13. 10/4 Logical Agents (part II) Chapter 7 Task 3
14. 10/6 Paper 2 presentation    
15. 10/11 First Order Logic Chapter 8  
16. 10/13 Inference in First Order Logic Chapter 9 Task 4
  10/18 Spring Break – holiday    
17. 10/20 Uncertainty Chapter 13  
18. 10/25 Paper 3 presentation    
19. 10/27 Bayesian Networks Chapter 14  
20. 11/1 Inference in Bayesian networks Chapter 15 Task 5
21. 11/3 Review & QA    
22. 11/8 Midterm #2    
23. 11/10 Speech Recognition Chapter 15  
24. 11/15 Paper 4 presentation    
25. 11/17 Simple Decisions Chapter 16 Task 6
26. 11/22 Learning from Observations Chapter 18  
  11/24 Thanksgiving – holiday    
27. 11/29 Neural Networks Chapter 18  
28. 12/1 Statistical learning Chapter 20 Task 7
29. 12/6 Natural Language Processing Chapter 22  
30. 12/8 Review & QA    
         
  12/15 Final Exam 3:30pm to 5:30pm