CS 580-003 
Introduction to Artificial Intelligence
Meets
 Monday 1:30 pm - 4:10 pm Arlington: Fuse 1328
Professor
 Zoran Duric.
About the Class
  The course can be roughly divided in two
                parts: (i) Intelligence from computation including
                uninformed and informed search, adverserial search,
                constraint satisfaction, markov decison processes, and
                reinforcement learning; (ii) Intelligence from data
                including probailistic reasoning, and unsupervised and
                supervised machine learning methods.
  
Prerequisites
CS330 and CS310 OR CS530 and CS531, no exceptions.
Textbooks
  - Artificial Intelligence: A Modern Approach, 4th ed.,
  Russell & Norvig (recommended), Prentice Hall
  
- Artificial Intelligence, Poole & Mackworth, 3rd ed., Cambridge
  University Press (recommended), available online
  
Software
We will use Python for homework assignments and projects. 
 
Course Web Page
 We will communicate through
  canvas. Slides,
  handouts, and assignments will be posted on the canvas course
  page. We will answer questions in canvas.
Grading
 Grading will be based on a combination of the following factors:
  
    -  Projects: 10%
    
-  Homeworks: 10%
    
-  In class presentation(s): 10%
    
-  Quizzes: 10%
-  Midterm: 30%.
-  Final: 30%.
Honor Code
The class enforces the GMU Honor Code, and the more specific honor code policy special to the Department of Computer Science.  You will be expected to adhere to this code and policy.
Use of LLMs to complete assignments
I do not approve of using AI tools to complete homework assigments and
projects. Please note that AI
tools will not be avilable in exams.
Disabilities
If you have a documented learning disability or other condition which may affect academic performance, make sure this documentation is on file with the Office of Disability Services and come talk to me about accommodations.
Course Outcomes
 
 
1. A knowledge of basic uninformed and heuristic search techniques. 
2. A knowledge of basic logic or probabilistic reasoning techniques. 
3. A knowledge of basic machine learning techniques. 
4. An ability to implement basic AI methods in Python. 
5. An ability to identify and apply an appropriate AI method to a given problem.