COURSE UNIT TITLE

: NEURAL NETWORK APPLICATIONS IN MECHATRONIC SYSTEMS

Description of Individual Course Units

Course Unit Code Course Unit Title Type Of Course D U L ECTS
MEC 5009 NEURAL NETWORK APPLICATIONS IN MECHATRONIC SYSTEMS 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

ASISTANT PROFESSOR AHMET ÖZKURT

Offered to

M.Sc. Mechatronics Engineering
Mechatronics Engineering

Course Objective

The course aims to provide an introduction about neural Networks (NN) for mechatronic systems. Fundamental knowledge, neural network types and application to a basic robotics system is planned to conluded.

Learning Outcomes of the Course Unit

1   The students are expected to learn basics of neural approach and comparison with human brain
2   The students are expected to understand learning mechanisms of neurons.
3   The students are expected to get information in different neural network structures
4   The students are expected to gain basic skills about the application of neural Networks in practical mechatronics systems
5   The students are expected to prepare a technical report about the Project proposals.

Mode of Delivery

Face -to- Face

Prerequisites and Co-requisites

None

Recomended Optional Programme Components

None

Course Contents

Week Subject Description
1 Introduction to smart systems, neural network, fuzzy logic and genetic algorithms
2 Fundamentals of Neural Behaviour
3 Neural network types and learning rules
4 Adaline and Madaline
5 Learning Process
6 Perceptron model
7 Multilayer perceptrons, backpropagation
8 Midterm
9 Hopfield Networks
10 SOM Networks
11 Neural Features of Mechatronic systems
12 Robot Design for Neural Application for line following Robot
13 Student Presentations
14 Student Presentations

Recomended or Required Reading

Textbook(s): Neural Networks: A Comprehensive Foundation (2nd Edition), 1998, Simon Haykin, ISBN: 0132733501, Prentice Hall
Neural Networks and Learning Machines, (3rd Edition), 2008, Simon Haykin, ISBN: 0131471392

Planned Learning Activities and Teaching Methods

The course is taught in a lecture, class presentation, discussion and project format. All class members are expected to attend and both the lecture and seminar hours, to take part in the discussion sessions and to prepare two main system design projects.

Assessment Methods

SORTING NUMBER SHORT CODE LONG CODE FORMULA
1 MTE MIDTERM EXAM
2 ASG ASSIGNMENT
3 PRS PRESENTATION
4 FIN FINAL EXAM
5 FCG FINAL COURSE GRADE MTE* 0.30 + ASG * 0.20 + PRS * 0.10 + FIN * 0.40
6 RST RESIT
7 FCGR FINAL COURSE GRADE (RESIT) MTE* 0.30 + ASG * 0.20 + PRS * 0.10 + RST * 0.40


Further Notes About Assessment Methods

None

Assessment Criteria

Midterm and final exam:
1. The students are expected to learn basics of neural approach and comparison with human brain
2. The students are expected to understand learning mechanisms of neurons.
3. The students are expected to get information in different neural network structures
4. The students are expected to gain basic skills about the application of neural Networks in practical mechatronics systems

Homework:
1. The students are expected to learn basics of neural approach and comparison with human brain
2. The students are expected to understand learning mechanisms of neurons.
3. The students are expected to get information in different neural network structures
4. The students are expected to gain basic skills about the application of neural Networks in practical mechatronics systems
5. The students are expected to prepare a technical report about the Project proposals.

Language of Instruction

English

Course Policies and Rules

To be announced.

Contact Details for the Lecturer(s)

: ahmet.ozkurt@deu.edu.tr
tel: 0232 3017134
ahmetozkurt.net

Office Hours

2 hours per week

Work Placement(s)

None

Workload Calculation

Activities Number Time (hours) Total Work Load (hours)
Lectures 13 3 39
Preparations before/after weekly lectures 13 3 39
Preparation for midterm exam 1 10 10
Preparing presentations 1 50 50
Preparing assignments 1 30 30
Preparation for final exam 1 20 20
Midterm 1 3 3
Final 1 3 3
TOTAL WORKLOAD (hours) 194

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.1322
LO.2322
LO.343
LO.44432
LO.533332232