|
|
| BILB3001 | Introduction to Artificial Intelligence | 4+0+0 | ECTS:6 | | Year / Semester | Fall Semester | | Level of Course | First Cycle | | Status | Compulsory | | Department | COMPUTER SCIENCE | | Prerequisites and co-requisites | None | | Mode of Delivery | | | Contact Hours | 14 weeks - 4 hours of lectures per week | | Lecturer | Prof. Dr. Orhan KESEMEN | | Co-Lecturer | | | Language of instruction | Turkish | | Professional practise ( internship ) | None | | | | The aim of the course: | | To teach students different approaches to problem solving, to give basic knowledge in the field of machine learning, to research and apply different approaches in the fields of computer vision and natural language processing. |
| Learning Outcomes | CTPO | TOA | | Upon successful completion of the course, the students will be able to : | | | | LO - 1 : | will be able to learn and apply different approaches to problem solving | 10,11 | 1,3, | | LO - 2 : | They take basic knowledge and apply it in the field of machine learning | 10,11 | 1,3, | | LO - 3 : | investigate and apply different approaches in the fields of computer vision and natural language processing | 10,11 | 1,3, | | LO - 4 : | They can solve problems and write programs with an intuitive approach | 10,11 | 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: Learning basic AI techniques, applicable examples and examining their limitations; State Space Searches: Definition of problem space, operators, state space searches, objective state; Blind Arams: learning basic search strategies; Heuristic Searches: Learning the heuristic evaluation function; Techniques for climbing the hill; Best First Search: Learning the best search and A* searches; comparison of different search algorithms; Intuitive functions; Minimax Calls: Learning two-player games; learning the game evaluation function; learning minimax searches; Learning depth limits; learning Alpha beta, acceptable heuristic searches for MiniMax; Expert Mechanisms: Learning Expert Mechanisms; Natural Language Processing: Problems in Natural Language processing; Grammar, Extraction, Definition of grammatical sentence; Creation of the weeding tree; Computational Learning: The purpose of learning programs; Evaluation of learning programs; conjunction rules; Classification with decision tree; Learning the decision tree. |
| |
| Course Syllabus | | Week | Subject | Related Notes / Files | | Week 1 | Introduction to Artificial Intelligence: Learning basic AI techniques, applicable examples and examining their limitations; | | | Week 2 | State Space Searches: Defining the problem space, operators, state space searches, intent state; | | | Week 3 | Blind Searches: learning basic search strategies; | | | Week 4 | Week 4 Heuristic Searches: Learning the heuristic evaluation function; | | | Week 5 | Techniques for climbing the hill; | | | Week 6 | Best First Search: Learning the best search and A* searches; | | | Week 7 | Comparison of different search algorithms; | | | Week 8 | Intuitive functions; Minimax Calls: Learning two-player games; | | | Week 9 | Midterm Exam | | | Week 10 | Learning the game evaluation function; learning minimax calls | | | Week 11 | Learning depth limits; learning Alpha beta, acceptable heuristic searches for MiniMax; | | | Week 12 | Expert Mechanisms: Learning Expert Mechanisms; | | | Week 13 | Natural Language Processing: Problems in Natural Language processing; | | | Week 14 | Grammar, Extraction, Definition of grammatical sentence; Creation of the weeding tree; | | | Week 15 | Computer Learning: The purpose of learning programs; Evaluation of learning programs; | | | Week 16 | Final exam | | | |
| 1 | Stuart Russell and Peter Norvig, Artificial Intelligence A Modern Approach, Prentice-Hall (2003 - 2nd Edition) | | | |
| 1 | Vasif V. NABİYEV, 2003, Artificial Intelligence, problems, methods, algorithms, Seçkin Publishing House, Ankara | | | |
| Method of Assessment | | Type of assessment | Week No | Date | Duration (hours) | Weight (%) | | Mid-term exam | 9 | | 1 | 30 | | Homework/Assignment/Term-paper | 2,3,4,5,6,7,8,10,11,12 | | 1 | 20 | | 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 | 4 | 14 | 56 | | Sınıf dışı çalışma | 1 | 14 | 14 | | Arasınav için hazırlık | 1 | 8 | 8 | | Arasınav | 1 | 1 | 1 | | Ödev | 1 | 14 | 14 | | Dönem sonu sınavı için hazırlık | 1 | 6 | 6 | | Dönem sonu sınavı | 1 | 1 | 1 | | Total work load | | | 100 |
|