COURSE UNIT TITLE

: METHODS OF ARTIFICAL INTELLIGENCE

Description of Individual Course Units

Course Unit Code Course Unit Title Type Of Course D U L ECTS
ETE 3005 METHODS OF ARTIFICAL INTELLIGENCE ELECTIVE 2 0 0 4

Offered By

Faculty of Engineering

Level of Course Unit

First Cycle Programmes (Bachelor's Degree)

Course Coordinator

ASISTANT PROFESSOR ÖZLEM AKTAŞ

Offered to

Industrial Engineering
Electrical and Electronics Engineering
Textile Engineering
Mechanical Engineering
Civil Engineering
Geological Engineering
Geophysical Engineering
Mining Engineering
Metallurgical and Materials Engineering
Environmental Engineering
Civil Engineering
Mining Engineering
Geological Engineering
Mechanical Engineering

Course Objective

The main objectives of this course are to discuss, teach and apply the methods, languages, and search paradigms in AI.; increase the abilities of analytical and theoretical thinking of students, so make them able to solve the problems efficiently.

Learning Outcomes of the Course Unit

1   Learn methods and applications of artificial inteligence in daily life.
2   Learn and implement the necessary search paradigms for the solutions of mathematical problems, such as constrait satisfaction problems, when needed.
3   Learn techniques in Artificial Intelligence.
4   Understand and apply learning paradigms in daily life and solve the problems.

Mode of Delivery

Face -to- Face

Prerequisites and Co-requisites

None

Recomended Optional Programme Components

None

Course Contents

Week Subject Description
1 Introduction to Artificial Intelligence: History and Applications
2 Knowledge Representation with AI Applications
3 Problem Solving: Constraint Satisfaction Problems (CSP), Backtracking Search for CSP
4 Search Strategies - I: State Space Search (Depth First, Breath First), Heuristic Search
5 Search Strategies - II: Hill Climbing, Best First Search, A* Method
6 Game Trees and Adversary Search, Alpha Beta Pruning, Min Max Approach
7 Midterm I
8 Techniques in Artificial Intelligence I
9 Techniques in Artificial Intelligence II
10 Learning Methods - I: Learning from Observations, Inductive Learning, Decision Trees
11 Learning Methods - II: Learning from Examples, Learning with Hidden Variables, Instance Based Learning
12 Natural Language Processing: Syntax, Semantics and Pragmatics - I
13 Natural Language Processing: Syntax, Semantics and Pragmatics - II
14 Intelligent Agents

Recomended or Required Reading

Text Book: Artificial Intelligence A Modern Approach,Stuart Russell,Peter Norvig, Prentice Hall,0131038052,New Jersey,1995
Supplementary Book: Artificial Intelligence, George Luger, Addison Wesley, 0201648660, England, 2002

Planned Learning Activities and Teaching Methods

Presentation, Problem Solving, Homework, Laboratory

Assessment Methods

SORTING NUMBER SHORT CODE LONG CODE FORMULA
1 MTE MIDTERM EXAM
2 ASG ASSIGNMENT
3 FIN FINAL EXAM
4 FCG FINAL COURSE GRADE MTE*0.35+ASG *0.15+FIN * 0.50
5 RST RESIT
6 FCG FINAL COURSE GRADE MTE*0.35+ASG *0.15+RST * 0.50

Further Notes About Assessment Methods

None

Assessment Criteria

Midterm exam is 25 %, assignments are 25%, final exam is 50% of the course grade.

Language of Instruction

English

Course Policies and Rules

To be announced.

Contact Details for the Lecturer(s)

Asst.Prof.Dr. Özlem AKTAŞ

Computer Engineering Department
Dokuz Eylul Unv. Tinaztepe Campus Buca Izmir

ozlem@cs.deu.edu.tr,
aktas.ozlem@deu.edu.tr,
0232 3017426

Office Hours

To be announced.

Work Placement(s)

None

Workload Calculation

Activities Number Time (hours) Total Work Load (hours)
Lectures 13 2 26
Preparations before/after weekly lectures 13 1 13
Preparation for midterm exam 1 12 12
Preparation for final exam 1 12 12
Preparing assignments 2 6 12
Preparing presentations 2 5 10
Final 1 3 3
Midterm 1 2 2
TOTAL WORKLOAD (hours) 90

Contribution of Learning Outcomes to Programme Outcomes

PO/LOPO.1PO.2PO.3PO.4PO.5PO.6PO.7PO.8PO.9PO.10PO.11PO.12PO.13
LO.12211255
LO.24532224
LO.33111511
LO.45544134