|
|
| TBIL2027 | Introduction to Artificial Intelligence | 2+0+0 | ECTS:3 | | Year / Semester | Fall Semester | | Level of Course | Short Cycle | | Status | Elective | | Department | DEPARTMENT of COMPUTER TECHNOLOGIES | | Prerequisites and co-requisites | None | | Mode of Delivery | | | Contact Hours | 14 weeks - 2 hours of lectures per week | | Lecturer | Dr. Öğr. Üyesi Ercüment YILMAZ | | Co-Lecturer | | | Language of instruction | Turkish | | Professional practise ( internship ) | None | | | | The aim of the course: | | To gain knowledge about the development and fundamental algorithms of Artificial Intelligence and to acquire the ability to develop applications using AI techniques. |
| Learning Outcomes | CTPO | TOA | | Upon successful completion of the course, the students will be able to : | | | | LO - 1 : | Understanding AI search models and social search strategies. | 6 | 1, | | LO - 2 : | Using Bayesian networks and probability as a mechanism for handling uncertainty in Artificial Intelligence. | 6 | 1,3, | | LO - 3 : | Investigating the design of Artificial Intelligence systems that attempt to perform a task better by using learning. | 6 | 1,3, | | CTPO : Contribution to programme outcomes, TOA :Type of assessment (1: written exam, 2: Oral exam, 3: Homework assignment, 4: Laboratory exercise/exam, 5: Seminar / presentation, 6: Term paper), LO : Learning Outcome | | |
| Introduction to artificial intelligence and basic concepts, history of artificial intelligence, intelligent agents, problem solving: problem-solving agents and problem formulation, search strategies, non-heuristic search: breadth-first search, depth-first search, uniform-cost search, depth-limited search, iterative depth search, two-way search, heuristic search methods; Greedy, A* search, simulated annealing method, hill climbing algorithm, local beam algorithm, genetic algorithms, genetic algorithms and their applications, searching in non-deterministic motions, searching in unobservable situations, searching in partial observation, searching in games, minimax algorithm, alpha-beta pruning, searching in stochastic games, condition satisfaction problems. |
| |
| Course Syllabus | | Week | Subject | Related Notes / Files | | Week 1 | Introduction to artificial intelligence and basic concepts, history of artificial intelligence.
| | | Week 2 | Intelligent agents | | | Week 3 | Problem solving: problem-solving factors and problem formulation. | | | Week 4 | Search strategies, non-heuristic search: breadth-first search, depth-first search, | | | Week 5 | Uniform-cost search, depth-limited search | | | Week 6 | Iterative deep search, two-way search | | | Week 7 | Applications of non-heuristic search methods | | | Week 8 | Heuristic search methods; Greedy and A* search. | | | Week 9 | Mid-term exam | | | Week 10 | Applications of heuristic search methods
| | | Week 11 | Hill climbing algorithm, simulated annealing method, local beam algorithm, genetic algorithms
| | | Week 12 | Genetic algorithms and their applications
| | | Week 13 | Searching in non-deterministic motion, searching in situations where observation is impossible, searching in partial observation.
| | | Week 14 | Search in games, minimax algorithm, alpha-beta pruning, stochastic games.
| | | Week 15 | artificial neural networks
| | | Week 16 | Final exam
| | | |
| 1 | Mitchell H. Q.,Parker S, 2004, Live English Grammer, Elementary, Great Britain | | | |
| Method of Assessment | | Type of assessment | Week No | Date | Duration (hours) | Weight (%) | | Mid-term exam | 9 | | 1 | 50 | | End-of-term exam | 16 | | 1 | 50 | | |
| Student Work Load and its Distribution | | Type of work | Duration (hours pw) | No of weeks / Number of activity | Hours in total per term | | Yüz yüze eğitim | 3 | 14 | 42 | | Sınıf dışı çalışma | 1 | 14 | 14 | | Arasınav için hazırlık | 1 | 7 | 7 | | Arasınav | 1 | 1 | 1 | | Dönem sonu sınavı için hazırlık | 1.5 | 6 | 9 | | Dönem sonu sınavı | 1 | 1 | 1 | | Diğer 1 | 1 | 1 | 1 | | Total work load | | | 75 |
|