COURSE UNIT TITLE

: INTRODUCTION TO ARTIFICIAL INTELLIGENCE

Description of Individual Course Units

Course Unit Code Course Unit Title Type Of Course D U L ECTS
CME 4418 INTRODUCTION TO ARTIFICIAL INTELLIGENCE ELECTIVE 2 2 0 6

Offered By

Computer Engineering

Level of Course Unit

First Cycle Programmes (Bachelor's Degree)

Course Coordinator

ASISTANT PROFESSOR ÖZLEM AKTAŞ

Offered to

Computer 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   Use appropriate search paradigm for problem solving and produce solutions for the given problems.
4   Implement programmes with Artificial Intelligence languages (Prolog, etc.).
5   Make Artificial Intelligence based programming with modern programlamming languages (Java, C, C++, C#, etc.).
6   Understand learning paradigms.
7   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: State Space Search (Depth First, Breath First), Heuristic Search
5 Hill Climbing, Best First Search, A* Method
6 Game Trees and Adversary Search,Alpha Beta Pruning, Min Max Approach
7 Midterm 1
8 AI Languages and Knowledge Database Representation, Introduction to Prolog, Programming with Prolog
9 Natural Language Processing: Syntax, Semantics and Pragmatics, AI and Robotics
10 Learning Paradigms: Learning from Observations, Inductive Learning, Decision Trees
11 Learning Paradigms: Learning from Examples, Learning with Hidden Variables, Instance Based Learning
12 Neural Networks, Intelligent Agents
13 Midterm 2
14 Expert Systems

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 QUZ QUIZ
3 FIN FINAL EXAM
4 FCG FINAL COURSE GRADE MTE*0.35+QUZ *0.15+FIN * 0.50
5 RST RESIT
6 FCG FINAL COURSE GRADE MTE*0.35+QUZ *0.15+RST * 0.50

Further Notes About Assessment Methods

None

Assessment Criteria

1st and 2nd midterm exams are 15 % each, lab assignments are 5%, 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)

ozlem@cs.deu.edu.tr, aktas.ozlem@deu.edu.tr, 02323017426

Office Hours

Tuesday 10:00 - 12:00, Wednesday 10:00 - 12:00

Work Placement(s)

None

Workload Calculation

Activities Number Time (hours) Total Work Load (hours)
Lectures 10 2 20
Tutorials 10 2 20
Preparation for quiz etc. 2 3 6
Preparing presentations 1 8 8
Preparations before/after weekly lectures 12 2 24
Preparation for final exam 1 10 10
Preparing assignments 3 8 24
Preparation for midterm exam 2 8 16
Final 1 4 4
Midterm 2 2 4
Quiz etc. 2 1 2
TOTAL WORKLOAD (hours) 138

Contribution of Learning Outcomes to Programme Outcomes

PO/LOPO.1PO.2PO.3PO.4PO.5PO.6PO.7PO.8PO.9PO.10
LO.15555332
LO.2545
LO.34535524
LO.444233
LO.554233
LO.634
LO.7245231