COURSE UNIT TITLE

: ARTIFICIAL NEURAL NETWORKS

Description of Individual Course Units

Course Unit Code Course Unit Title Type Of Course D U L ECTS
EEE 5029 ARTIFICIAL NEURAL NETWORKS ELECTIVE 3 0 0 7

Offered By

Graduate School of Natural and Applied Sciences

Level of Course Unit

Second Cycle Programmes (Master's Degree)

Course Coordinator

ASSOCIATE PROFESSOR YAVUZ ŞENOL

Offered to

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

Course Objective

The objectives of the course are:
- to present the basic network architectures and learning rules;
- to provide mathematical methods for neural network analysis and design;
- to provide knowledge for network training and overfitting avoidance;
- to apply neural networks to practical engineering problems in areas of function approximation, pattern recognition, and signal processing.

Learning Outcomes of the Course Unit

1   Describe the relation between real brain and artificial neural network models
2   To be able to design single and multi-layer feed-forward neural networks
3   To be able to explain the differences between supervised and unsupervised learning
4   To be able to explain the behavior or neural networks of the Back-prop, RBF, Hopfield and SOM type
5   To be able to implement ANN algorithms to various engineering problems
6   To be able to analyse the performance of neural networks

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. Biological neurons and neural Networks and their comparison
2 Networks of artificial neurons. Single layer perceptrons.
3 Basic learning rules; generalized LMS, and Hebbian Learning
4 Data processing; Scaling, Transformations, FT, PCA, and wavelets
5 Multi-layer perceptrons and backpropagation.
6 Learning with momentum and Conjugate Gradient Learning
7 Fitting problems and improving generalization
8 Applications of MLPNN
9 Project Evaluation
10 Radial Basis Function Neural Networks
11 Self Organising Networks and Learning Vector Quantization
12 Recurrent Networks
13 Project evaluation
14 Project evaluation

Recomended or Required Reading

Main Sources: Principles of Neurocomputing for Science & Engineering, McGraw Hill, 2001
Suplementary Sources: Neural Networks A Comprehensive Foundation, Simon Haykın Prentice Hall, 1999
Other Materials: Course notes.

Planned Learning Activities and Teaching Methods

Lecture+Homeworks+Project +Exam

Assessment Methods

SORTING NUMBER SHORT CODE LONG CODE FORMULA
1 ASG ASSIGNMENT
2 FIN FINAL EXAM
3 FCG FINAL COURSE GRADE ASG * 0.50 + FIN * 0.50
4 RST RESIT
5 FCGR FINAL COURSE GRADE (RESIT) ASG * 0.50 + RST * 0.50


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

Further Notes About Assessment Methods

None

Assessment Criteria


Language of Instruction

English

Course Policies and Rules

To be announced.

Contact Details for the Lecturer(s)

yavuz.senol@deu.edu.tr

Office Hours

Posted each term

Work Placement(s)

None

Workload Calculation

Activities Number Time (hours) Total Work Load (hours)
Lectures 13 3 39
Preparations before/after weekly lectures 14 4 56
Preparation for final exam 1 20 20
Preparing presentations 1 10 10
Preparing assignments 5 5 25
Preparation for project 1 20 20
Final 1 2 2
TOTAL WORKLOAD (hours) 172

Contribution of Learning Outcomes to Programme Outcomes

PO/LOPO.1PO.2PO.3PO.4PO.5PO.6PO.7PO.8PO.9PO.10PO.11PO.12PO.13PO.14PO.15
LO.111
LO.2211
LO.31114111
LO.4223112122112
LO.535344211211111
LO.63433411121111