Information Package / Course Catalogue
Course Code: 
Course Type: 
Couse Group: 
Education Language: 
Work Placement: 
Theory: 0
Prt.: 0
Credit: 0
Lab: 0
ECTS: 
Objectives of the Course

Course Content

Name of Lecturer(s)
Assoc. Prof. Coşkun DENİZ
Learning Outcomes
1.To gain the ability to apply the basic concepts, techniques, mathematics and software infrastructure of artificial neural networks.
2.To recognize and use the ANN tools that are widely used today. To obtain the basic information necessary to create ANN libraries in new programming languages (such as Java, C #, python). To be able to develop projects in real life such as Estimation, Classification and Recognition.
3.To be able to develop intelligent software; to understand how machines can learn; To be able to make effective ANN designs.
4.Being able to follow the research topics developing in the field of Image Processing; To be able to make presentations by preparing short seminars on this subject.
5.To gain experience in reading and writing articles.
Recommended or Required Reading
1.Prof. Dr. Ercan Öztemel, 2003, “Yapay Sinir Ağları”, Papatya Yayıncılık, 238s. (Ders Kitabı).
2.Prof. Dr. Çetin Elmas, 2007, "Yapay Zeka Uygulamaları", Seçkin Yayıncılık, 425 s.
3.Haykin, Simon, 1998, “Neural Networks: A Comprehensive Fo-undation (2nd Edition)”, Prentice-Hall, 842p.
Weekly Detailed Course Contents
Week 1 - Theoretical & Practice
Motivation and importance of the course, Introduction to Artificial Neural Networks (ANNs): Definition and importance of ANN, ANN tools and software, their application areas and job opportunities.
Week 2 - Theoretical & Practice
Artificial Intelligence (AI): Definition of AI, its importance, its subfields and subjects, its application and research areas, AI languages
Week 3 - Theoretical & Practice
Fundamentals of ANN: Artificial neuron and components, types of activation functions, biological neuron, biological nervous system, comparison of human brain and ANN.
Week 4 - Theoretical & Practice
Machine Learning (ML), supervised and unsupervised learning, estimation, classification and clustering by using ANN.
Week 5 - Theoretical & Practice
Single layer perceptron: examples of perceptron and ADALINE.
Week 6 - Theoretical & Practice
XOR Problem and need for multi-layer models.
Week 7 - Theoretical & Practice
Multi Layer Perceptrons (MLP).
Week 8 - Theoretical & Practice
Review-Midterm Exam
Week 9 - Theoretical & Practice
Feed Forward Networks (FFNs), Python applications
Week 10 - Theoretical & Practice
Back Propagation Networks (BPNs) and mathematical modelling of learning
Week 11 - Theoretical & Practice
RBF (Radial Basis Function) Neural Networks.
Week 12 - Theoretical & Practice
LVQ (Learning Vector Quantization) Neural Networks.
Week 13 - Theoretical & Practice
SOM (Self-Organizing Maps) Neural Networks.
Week 14 - Theoretical & Practice
SOM (Self-Organizing Maps) Neural Networks.
Assessment Methods and Criteria
Type of AssessmentCountPercent
Assignment2%10
Term Assignment1%5
Project1%70
Midterm Examination1%15
Workload Calculation
ActivitiesCountPreparationTimeTotal Work Load (hours)
Lecture - Theory143384
Assignment25316
Term Project110212
Project156258
Midterm Examination128230
TOTAL WORKLOAD (hours)200
Contribution of Learning Outcomes to Programme Outcomes
PÇ-1
PÇ-2
PÇ-3
PÇ-4
PÇ-5
PÇ-6
PÇ-7
OÇ-1
3
3
3
3
4
3
4
OÇ-2
4
4
4
3
5
4
3
OÇ-3
3
3
5
5
5
4
3
OÇ-4
3
3
3
3
4
3
4
OÇ-5
4
4
4
4
4
4
4
Adnan Menderes University - Information Package / Course Catalogue
2026