COURSE UNIT TITLE

: INTRODUCTION TO ARTIFICIAL NEURAL NETWORKS

Description of Individual Course Units

Course Unit Code Course Unit Title Type Of Course D U L ECTS
MIF 5018 INTRODUCTION TO ARTIFICIAL NEURAL NETWORKS ELECTIVE 2 0 0 5

Offered By

Medical Informatics

Level of Course Unit

Second Cycle Programmes (Master's Degree)

Course Coordinator

ASSOCIATE PROFESSOR GÜLESER KALAYCI DEMIR

Offered to

Medical Informatics

Course Objective

In this course, It is aimed to give basic information to students regarding learning algorithms, neural networks and pattern recognition, image processing and computational vision applications. Three different types of learning, supervised, unsupervised and reinforcement learning applications will be explained and discussed.

Learning Outcomes of the Course Unit

1   Define the basic concepts associated with artificial neural networks
2   Use algorithms associated with artificial neural networks
3   Define the types of learning
4   Analyze the data by using the artificial neural networks algorithms
5   Apply the artificial neural networks algorithms onto the data in the field of health sciences

Mode of Delivery

Face -to- Face

Prerequisites and Co-requisites

None

Recomended Optional Programme Components

None

Course Contents

Week Subject Description
1 Introduction to neural networks
2 Neural model and network architectures
3 Visual examples
4 Learning model of back propagation algorithm
5 Overview of linear algebra
6 Evaluation
7 Mid-term exam
8 Hebbian learning
9 Performance surfaces and an overview of our Optimization
10 Widrow-Hoff learning
11 Geriyayılım
12 Associative learning
13 Assesment of final project
14 Evaluation
15 Final exam

Recomended or Required Reading

1) S. Haykin, Neural Networks: A Comprehensive Foundation 2nd edition, (Prentice Hall, 1999)
2) K. Mehrotra, C. Mohan, and S. Ranka, Elements of Artificial Neural Networks, MIT Press, 1997.
3) C. Looney, Pattern Recognition Using Neural Networks, Oxford University Press, 1997
4) C. Bishop, Neural Networks for Pattern Recognition, Oxford University Press, 1995.
5) J. Hertz, A. Krogh, R.G. Palmer, Introduction to the Theory of Neural Computation (Addison-Wesley, 1991)

Planned Learning Activities and Teaching Methods

Problem analysis, design and application, presentation/lecturing and interactive discussion.

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 * 0.30 + ODV * 0.40 + FIN* 0.30
5 RST RESIT
6 FCGR FINAL COURSE GRADE (RESIT) MTE * 0.30 + ODV * 0.40 + RST* 0.30


*** Resit Exam is Not Administered in Institutions Where Resit is not Applicable.

Further Notes About Assessment Methods

None

Assessment Criteria

Evaluation of homeworks, projects and exams

Language of Instruction

Turkish

Course Policies and Rules

Attendance is an essential requirement of this course and is the responsibility of the student. Students are expected to attend all lecture and recitation hours. Attendance must be at least 70% for the lectures.

Contact Details for the Lecturer(s)

Dokuz Eylül Üniversitesi, Faculty of Engineering, Department of Electrical and Electronics
e-mail: guleser.kalayci@deu.edu.tr
Tel: 0232 301 71 52

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 15 2 30
Preparation for midterm exam 1 15 15
Preparation for final exam 1 19 19
Preparing assignments 1 20 20
Preparing presentations 1 15 15
Final 1 2 2
Midterm 1 2 2
TOTAL WORKLOAD (hours) 129

Contribution of Learning Outcomes to Programme Outcomes

PO/LOPO.1PO.2PO.3PO.4PO.5PO.6PO.7PO.8PO.9PO.10PO.11PO.12PO.13PO.14PO.15PO.16
LO.155
LO.24555
LO.345
LO.454554
LO.555545