ARTIFICIAL NEURAL NETWORKS

EEM620

Course Code: EEM620
Semester: -
Theory+Practice: 3 + 0
ECTS: 10

Course Type

Elective Course

Course Level

Doctorate Of Science

Year of Study

Semester

ECTS

Name of Lecturer(s)

Professor Hamit Erdem

Learning Outcomes

At the end of this course, the students;

Understand and explain strengths and weaknesses of the neural-network algorithms discussed in class.
Gain an ability to determine under which circumstances neural networks are useful in real applications.
Gain an ability to distinguish between supervised and unsupervised learning and explain the key principles of the corresponding algorithms.
Gain an ability to select appropriate neural network architectures for a given application.
Gain an ability to use the MATLAB for programming ANN.

Mode of Delivery

Face to face

Prerequisites

Recommended Optional Programme Components

None

Course Description

General artificial neural network structures, feedforward and feedback networks, Hopfield, self organizing, radial basis function networks. Supervised and unsupervised learning, perceptron structures, backpropagation and other learning structures. Optimization methods, hierarchical networks and their applications.

Course Contents

WEEK	TOPICS
1^st Week	Introduction to artificial intelligence
2^nd Week	ANN and forward neural networks
3^rd Week	Learning algorithms and error based learning
4^th Week	Single layer perceptron, Adaline structure and LMS learning algorithm
5^th Week	Multilayer perceptron and back propagation learning algorithm
6^th Week	Multilayer perceptron and back propagation learning algorithm
7^th Week	RBF network
8^th Week	Midterm exam
9^th Week	Hopfield and unsupervised ANN
10^th Week	Hopfield and unsupervised ANN
11^th Week	SOM ANN
12^th Week	Project presentations
13^th Week	Project presentations
14^th Week	Project presentations

Recommended or Required Reading

1. Neural Networks, Simon Haykin, 2nd. Edition.
2. Artificial Intelligence: A Guide to Intelligent Systems", Negnevitsky, Second edition.

Planned Learning Activities and Teaching Methods

Presentation
Lecture
Questions/Answers

Assessment Methods and Criteria

	Quantity	Percentage (%)
Mid-term	1	30
Assignment	1	15
Project	1	25
Total(%)		70
Contribution of In-term Studies to Overall Grade(%)		70
Contribution of Final Examination to Overall Grade(%)		30
Total(%)		100

ECTS Allocated Based on Student Workload

Activities	Quantity	Duration (Hour)	Total Workload (Hour)
Midterm exam	1	3	3
Preparation for Quiz	0	0	0
Individual or group work	14	8	112
Preparation for Final exam	1	40	40
Course hours	14	3	42
Preparation for Midterm exam	1	30	30
Laboratory (including preparation)	0	0	0
Final exam	1	3	3
Homework	2	35	70
Total Work Load			300
Total Work Load / 30 (h)			10
ECTS Credit of the Course			10

Language of Instruction

Turkish

Work Placement(s)

Programme Qualifications / Learning Outcomes

	LO1	LO2	LO3	LO4	LO5
K1	X
K2		X	X		X
K3	X	X
K4				X	X
K5					X
K6
K7
K8
K9
K10
K11