COURSE UNIT TITLE

: NEURAL NETWORKS FOR SIGNAL PROCESSING

Description of Individual Course Units

Course Unit Code Course Unit Title Type Of Course D U L ECTS
EEE 5030 NEURAL NETWORKS FOR SIGNAL PROCESSING ELECTIVE 3 0 0 8

Offered By

Graduate School of Natural and Applied Sciences

Level of Course Unit

Second Cycle Programmes (Master's Degree)

Course Coordinator

ASSOCIATE PROFESSOR GÜLESER KALAYCI DEMIR

Offered to

ELECTRICAL AND ELECTRONICS ENGINEERING NON -THESIS (EVENING PROGRAM)
Industrial Ph.D. Program In Advanced Biomedical Technologies
Industrial Ph.D. Program In Advanced Biomedical Technologies
Biomedical Tehnologies (English)
ELECTRICAL AND ELECTRONICS ENGINEERING
ELECTRICAL AND ELECTRONICS ENGINEERING
ELECTRICAL AND ELECTRONICS ENGINEERING

Course Objective

The course aims the students: i) to learn artificial neural networks models and learning algorithms and ii) to use learning algorithms in designing artificial neural network models for processing speech, image, biological and other signals.

Learning Outcomes of the Course Unit

1   Be able to design artificial neural network models for a given specific signal processing application.
2   Be able to use artificial neural networks software packages.
3   Be able to identify the main implementational issues for common neural networks
4   Be able to explain the learning algorithms and generalization ability of ANN
5   Be able to implement the learning algorithms to different applications

Mode of Delivery

Face -to- Face

Prerequisites and Co-requisites

None

Recomended Optional Programme Components

None

Course Contents

Week Subject Description
1 Introduction to ANN, Historical progress of ANN.
2 Fundamentals of learning algorithms and ANN architectures
3 Single-Layer Discrete/Continous Valued Perceptron
4 Multi-Layer Feedforward Neural Networks
5 Multi-Layer Feedforward Neural Networks
6 Midterm
7 Feedback Neural Networks
8 NN Applications
9 Deep Feedforward Networks
10 Convolutional Neural Networks
11 Convolutional Neural Networks
12 NN Applications
13 Autoencoders
14 Deep Generative Models

Recomended or Required Reading

Neural Networks and Learning Machines (3rd Edition), Simon Haykin, Prentice Hall, 2009
Deep Learning, Ian Goodfellow,Yoshua Bengio and Aaron Courville, MIT Press,2016.
Introduction to Artificial Neural Systems, Jacek M. Zurada, PWS Publishing Company,1995

Planned Learning Activities and Teaching Methods

The course consists of lecture presentations, in-class group discussion on a specific problem and project based learning.

Assessment Methods

SORTING NUMBER SHORT CODE LONG CODE FORMULA
1 ASG ASSIGNMENT
2 MTE MIDTERM EXAM
3 FIN FINAL EXAM
4 FCG FINAL COURSE GRADE ASG * 0.30 + MTE * 0.30 + FIN * 0.40
5 RST RESIT
6 FCGR FINAL COURSE GRADE (RESIT) ASG * 0.30 + MTE * 0.30 + RST * 0.40


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

Further Notes About Assessment Methods

None

Assessment Criteria

To be announced.

Language of Instruction

English

Course Policies and Rules

To be announced.

Contact Details for the Lecturer(s)

Dokuz Eylul University,
Electrical and Electronics Engineering Department,
Tınaztepe Campus, Buca Izmir/Turkey
guleser.kalayci@deu.edu.tr
Tel: + 90 232 3017152

Office Hours

To be announced.

Work Placement(s)

None

Workload Calculation

Activities Number Time (hours) Total Work Load (hours)
Lectures 13 3 39
Preparing assignments 1 50 50
Preparations before/after weekly lectures 13 3 39
Preparation for midterm exam 1 18 18
Preparation for final exam 1 20 20
Preparing report 1 8 8
Reading 1 10 10
Final 1 2 2
Midterm 1 2 2
TOTAL WORKLOAD (hours) 188

Contribution of Learning Outcomes to Programme Outcomes

PO/LOPO.1PO.2PO.3PO.4PO.5PO.6PO.7PO.8PO.9PO.10
LO.1552532232
LO.2554421435
LO.3553422552
LO.4452321
LO.5