COURSE UNIT TITLE

: FUNDAMENTALS OF NEURAL NETWORKS

Description of Individual Course Units

Course Unit Code Course Unit Title Type Of Course D U L ECTS
EED 4013 FUNDAMENTALS OF NEURAL NETWORKS ELECTIVE 3 2 0 6

Offered By

Electrical and Electronics Engineering

Level of Course Unit

First Cycle Programmes (Bachelor's Degree)

Course Coordinator

ASSISTANT PROFESSOR NESLIHAN AVCU

Offered to

Electrical and Electronics Engineering

Course Objective

The aims of this course are to introduce the fundamental principles and techniques of artificial neural network systems
and to Investigate the principal neural network models and applications.

Learning Outcomes of the Course Unit

1   Be able to describe basics of artificial neural networks
2   Be able to use the most common ANN models and learning algorithms for specific applications
3   Be able to identify the main implementational issues for common neural network systems.
4   Be able to implement the algorithms by using a computer
5   Be able to explain the principles of supervised and unsupervised learning, and generalization ability of ANN

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 Fundamental Concepts and Models, General artificial Neuron Model
3 Supervised Learning, Single-Layer Discrete Valued Perceptron
4 Single layer, continuous valued perceptron. Nonlinear (sigmoidal) activation function.
5 Multilayer Feedforward Networks. Backpropagation Algorithm
6 Radial Basis Function Networks
7 Midterm
8 Associative Memories, Hopfield Networks
9 Unsupervised learning, Competetive networks
10 Matching and Self-Organizing Networks
11 Data preprocessing
12 Pattern recognition applications of artificial neural network
13 Control applications of artificial neural networks
14 Artificial neural networks as controllers

Recomended or Required Reading

Textbooks:
Neural Networks, Simon Haykin, Prentice Hall, 1998
Introduction to Artificial Neural Systems, Jacek M. Zurada, PWS Publishing Company, 1995
Recommended readings:
Neural Networks for Pattern Recognition, C.Bishop, Clarendon Press.
Other course materials: Lecture notes

Planned Learning Activities and Teaching Methods

A series of lectures on course materials will be given using PowerPoint presentations and blackboard. To support course materials, laboratory studies will be done.

Assessment Methods

SORTING NUMBER SHORT CODE LONG CODE FORMULA
1 MTE MIDTERM EXAM
2 PRJ PROJECT
3 LAB LABORATORY
4 FIN FINAL EXAM
5 FCG FINAL COURSE GRADE MTE * 0.25 + PRJ * 0.15 + LAB * 0.20 + FIN * 0.40
6 RST RESIT
7 FCGR FINAL COURSE GRADE (RESIT) MTE * 0.25 + PRJ * 0.15 + LAB * 0.20 + RST * 0.40


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

Further Notes About Assessment Methods

None

Assessment Criteria

Midterm exam, project, laboratory study, final exam

Language of Instruction

English

Course Policies and Rules

Rules related to the course will be announced on the course page.

Contact Details for the Lecturer(s)

Email: neslihan.avcu@deu.edu.tr

Tel: 0232 301 7681

Office Hours

To be announced at the beginning of the lectures.

Work Placement(s)

None

Workload Calculation

Activities Number Time (hours) Total Work Load (hours)
Lectures 13 3 39
Labratory 13 2 26
Preparations before/after weekly lectures 13 3 39
Preparation for midterm exam 1 8 8
Preparation for final exam 1 10 10
Project Preparation 1 20 20
Final 1 2 2
Midterm 1 2 2
TOTAL WORKLOAD (hours) 146

Contribution of Learning Outcomes to Programme Outcomes

PO/LOPO.1PO.2PO.3PO.4PO.5PO.6PO.7PO.8PO.9PO.10PO.11PO.12PO.13
LO.15
LO.2544
LO.355
LO.4352
LO.545