Türkçe|English  
  KTU Course Catalogue  
Arama Yapmak İstediğiniz Anahtar Kelimeyi Giriniz :       
FACULTY OF SCIENCE / STATISTICS AND COMPUTER SCIENCES
  General Information
  Administration
  Objectives & Learning Outcomes
  Academic Staff
  Curriculum
     First Year
     Second Year
     Third Year
     Fourth Year
   Learning Outcomes Matrix
 
  3rd Cycle Degree Programmes
  2nd Cycle Degree Programmes
  1st Cycle Degree Programmes
  Short Cycle Degree Programmes
 
  Back
  Catalog Main Page
  KTU Main Page

SEC 401 INTRODUCTION TO ARTIFICIAL INTELLIGENCE 4+0+0 ECTS:5
Year / Semester Fourth Year / Fall Semester
Level of CourseFirst Cycle
StatusElective
DepartmentSTATISTICS AND COMPUTER SCIENCES
Prerequisites and co-requisites None
Mode of DeliveryFace to face, Group study
Contact hours14 weeks - 4 hours of lectures per week
LecturerASSIST. PROF. DR. ORHAN KESEMEN
Co-LecturerNone
Language of instruction Turkish
Professional practise ( internship )None
 
Objectives 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 Outcomes

CTPO

TOA

Upon successful completion of the course, the students will be able to :

LO - 1 :

acquire knowledge of various approaches of problem solving and apply them

1,2,3,4,5,6,7,8,9,10,11

1,3

LO - 2 :

acquire knowledge of various approaches of base information about machine learning

4,9,10,11

1,3

LO - 3 :

research various approaches to computer vision and natural language processing.and apply them

4,9,10,11

1,3

LO - 4 :

create programs using heuristics for problem solving

4,9,10,11

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

 

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

 Week

Subject

Related Notes / Files

 Week 1

Introduction to Artificial Intelligence: Learn the basic AI techniques; applicable techniques and the examination of their limits

 Week 2

State Space Search: Defining the problems space,operators,state space search,its objective and condition

 Week 3

Blind Search: Learning about basic search strategies;

 Week 4

Heuristic Searches: Learning about heuristic evaluation functions;

 Week 5

Learning about top going techniques;

 Week 6

Best First Search: Learining about best first and A* searches;

 Week 7

Comparing various search algorithms;

 Week 8

Heuristic functions; Minimax Searches: Learning about two player games;

 Week 9

Mid-term exam

 Week 10

Learning about game evaluation functions; Learning about minimax searches;

 Week 11

Learning about depth limits; Learning about alpha beta; an acceptable heuristic search for minimax;

 Week 12

Expert Systems: Learn about Expert systems

 Week 13

Natural Language Processing:Problems in natural language processing;

 Week 14

Grammar, Parsing, Defining grammatical sentences,Building a Parse Tree

 Week 15

Computer Learning: Goals of Learning Programs; Evaluating Learning Programs;

 Week 16

End-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 assessment

Week No

Date

Duration (hours)

Weight (%)

Homework/Assignment/Term-paper

03040506070810111213

3

50

End-of-term exam

16

16/01/2014

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

Lectures (face to face teaching)

4

14

56

Own (personal) studies outside class

3

14

42

Homework

3

10

30

Own study for final exam

6

1

6

End-of-term exam

1

1

1

Total work load

135