EGE UNIVERSITY

GRADUATE SCHOOL OF NATURAL AND APPLIED SCIENCES
ENGINEERING SCIENCES

COMPUTER ENGINEERING DEPARTMENT

2016-2017 SPRING SEMESTER

Course	624 INTELLIGENT SYSTEMS (3+0)
Instructor	Prof. Dr. Aybars UĞUR
Course Place and Time	EGE University Computer Engineering Department B1 Room (Tuesday, 13:15-16:00)
Learning Outcomes	To learn basic concepts of Intelligent Systems, mathematical and software background; to have ability to apply Intelligent Systems to problems. To have both a general “breadth” knowledge of AI techniques, plus a deeper specialized knowledge of one particular sub-area within AI; how to combine or integrate them. To be able to design and implement own Intelligent system (IS) To learn ability to use and integrate Software Tools in Artificial Neural Networks, Genetic Algorithms, Fuzzy Logic, Expert Systems. To do research in state-of-the-art subjects of Intelligent Systems area; preparing and doing presentation. To gain experience in reading and writing papers in Intelligent Systems.
Description	Introduction to Intelligent Systems, Artificial Neural Networks, Evolutionary Computation, Fuzzy Logic, Expert Systems, Hybrid Intelligent Systems, Fuzzy Expert systems, Neural Expert Systems, Neuro-fuzzy Systems, Evolutionary Neural Networks.
Syllabus	TOPICS Intelligent Systems Rule-based Expert Systems Fuzzy Expert Systems Frame-based Expert Systems Machine Learning Artificial Neural Networks Evolutionary Computation Metaheuristic Algorithms Hybrid Intelligent Systems Knowledge Engineering and Data Mining Computer Vision Robotics
Textbook	Michael Negnevitsky, “Artificial Intelligence : A Guide to Intelligent Systems (3rd Edition)”, Addison Wesley, 2011.
Reference Books	Mircea Negoita, Daniel Neagu, Vasile Palade, “Computational Intelligence: Engineering of Hybrid Systems (Studies in Fuzziness and Soft Computing)”, Springer, 2005. Computational Intelligence: A Logical Approach. Poole, Mackworth and Goebel. Oxford University Press, 1998. Neuro-Fuzzy and Soft Computing. J.S.R. Jang, C.T. Sun, E.Mizutani. Prentice Hall 1997. Seven methods for transforming corporate data into business intelligence V Dhar & R Stein Prentice Hall 1997. Also Sample Papers will be given.
Links	http://en.wikipedia.org/wiki/Hybrid_intelligent_system http://www.slideshare.net/ikensolutions/hybrid-intelligent-systems-presentation
Prerequisites	Artificial Intelligence Basics: Problem solving, state space search, machine learning principles, pattern recognition, fundamentals of computer vision. Basic knowledge of probability, statistics, calculus and linear algebra.
Grading	Midterm Activities (50%) · Project (+ Paper) (30%) · Presentation 1 (10%) · Presentation 2 (10%) · Take-Home - Final Exam (50%) For the Take-Home and reports, students will be allowed a total of 5 (five) late days; each additional late day will incur a 10% penalty.