Advanced Artificial Intelligence (MDES677) Course Detail

Course Name	Course Code	Season	Lecture Hours	Application Hours	Lab Hours	Credit	ECTS
Advanced Artificial Intelligence	MDES677		3	0	0	3	5

Pre-requisite Course(s)
Consent of the Instructor

Course Language	English
Course Type	N/A
Course Level	Natural & Applied Sciences Master's Degree
Mode of Delivery	Face To Face
Learning and Teaching Strategies	Lecture.
Course Coordinator
Course Lecturer(s)
Course Assistants
Course Objectives	To introduce advanced concepts and different approaches to Artificial Intelligence (AI) (including symbolic and non-symbolic ones). To extent the engineering vision of the student.
Course Learning Outcomes	The students who succeeded in this course; To learn how to design an agent for a given problem. To be able to decide on and apply suitable AI technique(s) to a given problem
Course Content	Intelligent agents, problem solving by searching, informed/uninformed search methods, exploration, constraint satisfaction problems, game playing, knowledge and reasoning: first-order logic, knowledge representation, learning, selected topics: evolutionary computing, multiagent systems, artificial neural networks, ant colony optimization.

Weekly Subjects and Releated Preparation Studies

Week	Subjects	Preparation
1	Intelligent Agents	Chapters 1-2 from Russell & Norvig
2	Intelligent Agents	Chapter 1-2 from Russell & Norvig
3	Informed/Uninformed Search Methods, Exploration	Chapter 3-4 from Russell & Norvig
4	Informed/Uninformed Search Methods, Exploration	Chapter 3-4 from Russell & Norvig
5	Constraint Satisfaction Problems	Chapter 5 from Russell & Norvig
6	Constraint Satisfaction Problems	Chapter 5 from Russell & Norvig
7	Game Playing	Chapter 6 from Russell & Norvig
8	Knowledge and Reasoning : Logical Agents	Chapter 7 from Russell & Norvig
9	Knowledge and Reasoning : First-Order Logic	Chapter 8 from Russell & Norvig
10	Knowledge and Reasoning : Inference in First-Order Logic	Chapter 9 from Russell & Norvig
11	Selected Topics : Evolutionary Computing	Source #5
12	Selected Topics : Multiagent Systems	Source #4
13	Selected Topics : Neural Networks	Source #3
14	Selected Topics : At Colony Optimization	Source #1
15	Overall review	-
16	Final exam	-

Sources

Course Book	1. Artificial Intelligence: A Modern Approach (Second Edition). Stuart Russell and Peter Norvig, Prentice-Hall, 2003, ISBN: 0-13-790395
Other Sources	2. Ant Colony Optimization, Marco Dorigo and Thomas Stützle, MIT Press, 2004.
	3. Artificial Intelligence, Patrick H. Winston, Addison-Wesley, 1992.
	4. Introduction to the Theory of Neural Computation, J. Hertz, A. Krogh and R.G. Palmer, Addison-Wesley Publishing Company, 1991
	5. An Introduction to MultiAgent Systems, Wooldridge, M., John Wiley & Sons, 2002
	6. An Introduction to Genetic Algorithms, Melanie Mitchell, MIT Press, 1998

Evaluation System

Requirements	Number	Percentage of Grade
Attendance/Participation	-	-
Laboratory	-	-
Application	-	-
Field Work	-	-
Special Course Internship	-	-
Quizzes/Studio Critics	-	-
Homework Assignments	-	-
Presentation	1	10
Project	1	25
Report	-	-
Seminar	-	-
Midterms Exams/Midterms Jury	1	25
Final Exam/Final Jury	1	40
Toplam	4	100

Percentage of Semester Work	60
Percentage of Final Work	40
Total	100

Course Category

Core Courses	X
Major Area Courses
Supportive Courses
Media and Managment Skills Courses
Transferable Skill Courses

The Relation Between Course Learning Competencies and Program Qualifications

#	Program Qualifications / Competencies	Level of Contribution
#	Program Qualifications / Competencies	1	2	3	4	5
1	Ability to expand and get in-depth information with scientific researches in the field of mechanical engineering, evaluate information, review and implement.
2	Have comprehensive knowledge about current techniques and methods and their limitations in Mechanical engineering.
3	To complete and apply knowledge by using scientific methods using uncertain, limited or incomplete data; use information from different disciplines.
4	Being aware of the new and developing practices of Mechanical Engineering and being able to examine and learn when needed.
5	Ability to define and formulate problems related to Mechanical Engineering and develop methods for solving and apply innovative methods in solutions.
6	Ability to develop new and/or original ideas and methods; design complex systems or processes and develop innovative/alternative solutions in the designs.
7	Ability to design and apply theoretical, experimental and modeling based researches; analyze and solve complex problems encountered in this process.
8	Work effectively in disciplinary and multi-disciplinary teams, lead leadership in such teams and develop solution approaches in complex situations; work independently and take responsibility.
9	To establish oral and written communication by using a foreign language at least at the level of European Language Portfolio B2 General Level.
10	Ability to convey the process and results of their studies systematically and clearly in written and oral form in national and international environments.
11	To know the social, environmental, health, security, law dimensions, project management and business life applications of engineering applications and to be aware of the constraints of their engineering applications.
12	Ability to observe social, scientific and ethical values in the stages of data collection, interpretation and announcement and in all professional activities.

ECTS/Workload Table

Activities	Number	Duration (Hours)	Total Workload
Course Hours (Including Exam Week: 16 x Total Hours)	16	3	48
Laboratory
Application
Special Course Internship
Field Work
Study Hours Out of Class	16	2	32
Presentation/Seminar Prepration	3	5	15
Project	1	20	20
Report
Homework Assignments
Quizzes/Studio Critics
Prepration of Midterm Exams/Midterm Jury	1	8	8
Prepration of Final Exams/Final Jury	1	10	10
Total Workload			133