Türkçe | English
FACULTY of SCIENCE / DEPARTMENT of STATISTICS and COMPUTER SCIENCES

Course Catalog
http://www.ktu.edu.tr/isbb
Phone: +90 0462 +90 (462) 3773112
FENF
FACULTY of SCIENCE / DEPARTMENT of STATISTICS and COMPUTER SCIENCES /
Katalog Ana Sayfa
  Katalog Ana Sayfa  KTÜ Ana Sayfa   Katalog Ana Sayfa
 
 

IST4019Introduction to Artificial Intelligence4+0+0ECTS:6
Year / SemesterFall Semester
Level of CourseFirst Cycle
Status Elective
DepartmentDEPARTMENT of STATISTICS and COMPUTER SCIENCES
Prerequisites and co-requisitesNone
Mode of DeliveryFace to face, Practical
Contact Hours14 weeks - 4 hours of lectures per week
LecturerProf. Dr. Orhan KESEMEN
Co-LecturerDOCTOR LECTURER Tolga BERBER
Language of instructionTurkish
Professional practise ( internship ) None
 
The aim of the course:
To teach various approaches for problem solving, the basic knowledge in machine learning, and research various approaches in computer vision, natural language processing and to make the students apply them . The Topics covered include search (solving puzzles, playing games) , planning, logical inference (drawing conclusions from data) , expert systems, and machine learning.
 
Learning OutcomesCTPOTOA
Upon successful completion of the course, the students will be able to :
LO - 1 : acquire knowledge of various approaches of problem solving and apply them1,3,4,91,3
LO - 2 : acquire knowledge of various approaches of base information about machine learning1,3,4,91,3
LO - 3 : research various approaches to computer vision and natural language processing.and apply them1,3,4,91,3
LO - 4 : create programs using heuristics for problem solving1,3,4,91,3
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

 
Contents of the Course
Introduction to Artificial Intelligence: Learning the basic AI techniques; the problems for which they are applicable; their limitations. State Space Search: Defining the problems space, operators, state space search, goal state; Blind Search: Learning about a basic search strategy; Heuristic Search: Learning about heuristic evaluation functions; Learn about hill climbing techniques; Best First Search: Learn about best first and A* search; Compare various search algorithms; Heuristic functions; Minimax Search: Learning about two player games; Learning about game evaluation functions; Learning about minimax search; Learning about depth bounded search; Learning about alpha beta; an admissible search heuristic for minimax; Learning to identify best move from game tree and nodes proned by alpha beta cutoffs; Expert Systems: Learning about Expert systemsNatural Language Processing: Learning about- Problems in natural language processing; Grammars; Parsing; Defining clause Grammars; Building Parse Trees; Machine Learning: Learn about the Goals of Learning Programs; Evaluating Learning Programs; Learning Conjunctive Rules; Classifying with Decision Trees; Learning Decision Trees;
 
Course Syllabus
 WeekSubjectRelated Notes / Files
 Week 1Introduction to Artificial Intelligence: Learn the basic AI techniques; applicable techniques and the examination of their limits
 Week 2State Space Search: Defining the problems space,operators,state space search,its objective and condition
 Week 3Blind Search: Learning about basic search strategies;
 Week 4Heuristic Searches: Learning about heuristic evaluation functions;
 Week 5Learning about top going techniques;
 Week 6Best First Search: Learining about best first and A* searches;
 Week 7Comparing various search algorithms;
 Week 8Heuristic functions; Minimax Searches: Learning about two player games;
 Week 9Mid-term exam
 Week 10Learning about game evaluation functions; Learning about minimax searches;
 Week 11Learning about depth limits; Learning about alpha beta; an acceptable heuristic search for minimax;
 Week 12Expert Systems: Learn about Expert systems
 Week 13Natural Language Processing:Problems in natural language processing;
 Week 14Grammar, Parsing, Defining grammatical sentences,Building a Parse Tree
 Week 15Computer Learning: Goals of Learning Programs; Evaluating Learning Programs;
 Week 16End-of-term exam
 
Textbook / Material
1Stuart Russell and Peter Norvig, Artificial Intelligence A Modern Approach, Prentice-Hall (2003 - 2nd Edition)
 
Recommended Reading
1Vasif V. NABİYEV, 2003, Yapay Zeka, problemler ? yöntemler ? algoritmalar, Seçkin Yayınevi, Ankara
 
Method of Assessment
Type of assessmentWeek NoDate

Duration (hours)Weight (%)
Mid-term exam 9 25/11/2021 2 50
End-of-term exam 16 11/01/2022 2 50
 
Student Work Load and its Distribution
Type of workDuration (hours pw)

No of weeks / Number of activity

Hours in total per term
Yüz yüze eğitim 4 14 56
Sınıf dışı çalışma 3 14 42
Ödev 3 10 30
Dönem sonu sınavı için hazırlık 6 1 6
Dönem sonu sınavı 1 1 1
Total work load135