Course gal is expose students to the fundamental topics and techniques in artificial intelligence through lectures, problems and experiments
Prerequisite(s)
None
Corequisite(s)
None
Special Requisite(s)
Basic programming skills, basic statistics and mathematical logic knowledge and (in order to follow the course resources) basic English knowledge are necessary and sufficient.
Instructor(s)
Professor Ozan KOCADAĞLI
Course Assistant(s)
None
Schedule
Wednesday, Comp.Lab. II, 13:00-15:00
Thursday, 4C-03/05, 09:00-11:00
Oral lectures with power points, term project, lab applications with Java and C#
Principle Sources
Artificial Intelligence by Stuart Russell and Peter Norvig 2010
Java development package
OpenNeuro Platform, http://code.google.com/p/opennero/wiki/BuildingOpenNero
Other Sources
-
Course Schedules
Week
Contents
Learning Methods
1. Week
Introduction to Artificial Intelligence and intelligent agents
Oral Presentation
2. Week
Solving Problems by searching and Informed Search
Oral Presentation and Laboratory
3. Week
constraint satisfaction and adversarial search
Oral Presentation and Laboratory
4. Week
knowledge and reasoning, logical agents
Oral Presentation and Laboratory
5. Week
First Order Logic
Oral Presentation and Problem Solving
6. Week
Inference in first order logic
Oral Presentation and Problem Solving
7. Week
Knowledge Representation, Planning and acting in real World
Oral Presentation and Problem Solving
8. Week
Midterm Exam
Exam
9. Week
Uncertain knowledge and reasoning
Oral Presentation and Problem Solving
10. Week
Probablistic Reasoning and Probabilsitc Reasoning over time
Oral Presentation and Problem Solving
11. Week
Making simple and complex decisions
Oral Presentation and Problem Solving
12. Week
Learning from examples and knowledge in learning (Support Vector Machines and decision trees)
Oral Presentation and Laboratory
13. Week
Neural Networks
Oral Presentation and Laboratory
14. Week
Reinforcement Learning
Oral Presentation and Laboratory
15. Week
Finals Week
Exam
16. Week
Finals Week
Exam
17. Week
Finals Week
Exam
Assessments
Evaluation tools
Quantity
Weight(%)
Final Exam
1
100
Program Outcomes
PO-1
Interpreting advanced theoretical and applied knowledge in Mathematics and Computer Science.
PO-2
Critiquing and evaluating data by implementing the acquired knowledge and skills in Mathematics and Computer Science.
PO-3
Recognizing, describing, and analyzing problems in Mathematics and Computer Science; producing solution proposals based on research and evidence.
PO-4
Understanding the operating logic of computer and recognizing computational-based thinking using mathematics as a discipline.
PO-5
Collaborating as a team-member, as well as individually, to produce solutions to problems in Mathematics and Computer Science.
PO-6
Communicating in a foreign language, and interpreting oral and written communicational abilities in Turkish.
PO-7
Using time effectively in inventing solutions by implementing analytical thinking.
PO-8
Understanding professional ethics and responsibilities.
PO-9
Having the ability to behave independently, to take initiative, and to be creative.
PO-10
Understanding the importance of lifelong learning and developing professional skills continuously.
PO-11
Using professional knowledge for the benefit of the society.
Learning Outcomes
LO-1
Understand the main approaches to artificial intelligence such as heuristic search, game search, logical inference, statistical inference, decision theory, planning, machine learning, neural networks and natural language processing
LO-2
Recognize problems that may be solved using artificial intelligence
LO-3
Implement artificial intelligence algorithms for hands-on experience
LO-4
Explain recent developments in interdisciplinary fields on brain modeling and understanding how to link to AI and assess brain inspired learning algorithms at the end of course
LO-5
Make critical judgements based on experience of doing independent study and criticize research results
