COURSE UNIT TITLE

: NEURAL NETWORKS

Description of Individual Course Units

Course Unit Code Course Unit Title Type Of Course D U L ECTS
CSE 5013 NEURAL NETWORKS ELECTIVE 3 0 0 9

Offered By

Graduate School of Natural and Applied Sciences

Level of Course Unit

Second Cycle Programmes (Master's Degree)

Course Coordinator

PROFESSOR DOCTOR DERYA BIRANT

Offered to

Computer Engineering (Non-Thesis-Evening) (English)
Computer Engineering Non-Thesis (English)
Computer Engineering (English)
Computer Engineering (English)
COMPUTER ENGINEERING (ENGLISH)

Course Objective

The main objective of this course is to present various neural networks (Multilayer Perceptrons, Radial Basis Function Networks, Self Organizing Maps, etc.) and to apply them in the solution of engineering problems.

Learning Outcomes of the Course Unit

1   Describe the relation between real brains and simple artificial neural network models
2   Have detailed knowledge about various artificial neural networks
3   Analyze the performance of artificial neural networks
4   Understand the differences among various network types
5   Apply artificial neural networks in practical 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 Neural Networks and their History. Biological Neurons and Neural Networks. Artificial Neurons
2 Networks of Artificial Neurons. Single Layer Perceptrons. Learning and Generalization in Single Layer Perceptrons
3 Hebbian Learning. Gradient Descent Learning
4 The Generalized Delta Rule. Practical Considerations
5 Learning in Multi-Layer Perceptrons. Back-Propagation
6 Learning with Momentum. Conjugate Gradient Learning
7 Bias and Variance. Under-Fitting and Over-Fitting.
8 Deep Learning
9 Applications of Multi-Layer Perceptrons
10 Radial Basis Function Networks: Introduction
11 Radial Basis Function Networks: Algorithms, Applications Comittee MAchines
12 Self Organizing Maps: Fundamentals, Algorithms and Applications
13 Learning Vector Quantization (LVQ)
14 Project Presentations

Recomended or Required Reading

Textbook(s):
D. Graupe, Principles of Artificial Neural Networks, WSPC, 2013
C.C. Aggarwal, Neural Networks and Deep Learning: A Textbook, Springer, 2018

Supplementary Book(s):
S. Haykin, Neural Networks And Learning Machines, Pearson India, 2018
M.T. Hagan, H.B. Demuth, M.H. Beale, O. De Jesús, Neural Network Design, Martin Hagan, 2014

Planned Learning Activities and Teaching Methods

Lectures
Literature Review / Research
Presentation
Term Project
Report

Assessment Methods

SORTING NUMBER SHORT CODE LONG CODE FORMULA
1 ASG ASSIGNMENT
2 PRS PRESENTATION
3 FCG FINAL COURSE GRADE ASG * 0.50 + PRS * 0.50


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

Further Notes About Assessment Methods

None

Assessment Criteria

Course outcomes will be evaluated with the presentation of the student about a topic, literature review, and project / report prepared by the student.

Language of Instruction

English

Course Policies and Rules

Code writing knowledge and skills are required.
Participation is mandatory.

Contact Details for the Lecturer(s)

Prof.Dr. Derya BIRANT
Dokuz Eylul University
Department of Computer Engineering
Tinaztepe Campus 35390 Buca / IZMIR
Tel: +90 (232) 301 74 01
E-mail: derya@cs.deu.edu.tr

Office Hours

Tuesday 9:30 - 10:30

Work Placement(s)

None

Workload Calculation

Activities Number Time (hours) Total Work Load (hours)
Lectures 14 3 42
Preparations before/after weekly lectures 14 2 28
Web Search and Library Research 1 5 5
Reading 10 3 30
Project Preparation 1 65 65
Preparing presentations 1 30 30
Preparing report 1 25 25
TOTAL WORKLOAD (hours) 225

Contribution of Learning Outcomes to Programme Outcomes

PO/LOPO.1PO.2PO.3PO.4PO.5PO.6PO.7PO.8PO.9PO.10PO.11
LO.14
LO.2444
LO.35434
LO.4444
LO.5554