Information Package / Course Catalogue
Introduction to Artificial Neural Networks
Course Code: EE465
Course Type: Area Elective
Couse Group: First Cycle (Bachelor's Degree)
Education Language: English
Work Placement: N/A
Theory: 3
Prt.: 0
Credit: 3
Lab: 0
ECTS: 5
Objectives of the Course

It is aimed to give the theoretical and practical knowledge to the students about artificial neural networks.

Course Content

Basic Artificial Neural Networks, Statistical Pattern Recognition, Classification, Single Layer Networks, Multilayer Networks - Fault Backward Spreading Models, Radial Based Functions, Error Functions, Supervised learning, Python applications.

Name of Lecturer(s)
Assoc. Prof. Coşkun DENİZ
Learning Outcomes
1.To be able to define the relation between brain and simple artificial neural network models
2.Multilevel Predseptran, radial basis function networks, learning algorithms for Kohonen self-organizing maps and the most common architectural structures
3.To be able to distinguish between different neural network architectures, their limitations and appropriate learning rules for each architecture
4.To be able to do engineering applications by understanding the classifications and models of learning types
5.To get the introductory knowledge on artificial intelligence and deep learning subjects
6.To be able to explain and demonstrate how this problem can be solved by determining the linear discriminability problem encountered in single-layer networks and adding hidden layers
7.To be able to discuss the main factors involved in creating a good learning and generalization achievement in artificial neural network systems
Recommended or Required Reading
1. S. Haykin, Neural Networks: A Comprehensive Foundation (2nd Edition), Prentice-Hall, 1998
2.S. Haykin, Neural Networks and Learning Machines (3rd Edition), Pearson, 2009.
3.F. Chollet, Deep Learning with Python, Manning, 2018.
4.Lecture notes and internet sources recommended.
Weekly Detailed Course Contents
Week 1 - Theoretical
Introduction to artificial neural networks
Week 2 - Theoretical
Creation of artificial neural networks
Week 3 - Theoretical
Creation of artificial neural networks: Perceptron, Delta rule
Week 4 - Theoretical
Creation of artificial neural networks: forward feed networks, feedback networkss.
Week 5 - Theoretical
Structures of artificial neural networks: Back propagation network, Delta bar delta.
Week 6 - Theoretical
Structures of artificial neural networks: Hopfield network, Hamming network.
Week 7 - Theoretical
Artificial neural network learning: Learning types, Supervised learning
Week 8 - Theoretical
Learning in Artificial Neural Networks: Supervised learning, perceptron learning rule
Week 9 - Theoretical
Learning in Artificial Neural Networks: Supervised learning, delta learning rule
Week 10 - Theoretical
Learning in Artificial Neural Networks: Supervised learning, Backpropagation learning
Week 11 - Theoretical
Learning in Artificial Neural Networks: Unsupervised learning
Week 12 - Theoretical
Introduction to Deep Neural Networks, Convolutional neural network (CNN)
Week 13 - Theoretical
Python applications
Week 14 - Theoretical
Python applications
Assessment Methods and Criteria
Type of AssessmentCountPercent
Midterm Examination1%30
Final Examination1%50
Quiz2%20
Workload Calculation
ActivitiesCountPreparationTimeTotal Work Load (hours)
Lecture - Theory141356
Individual Work140228
Quiz24010
Midterm Examination110212
Final Examination117219
TOTAL WORKLOAD (hours)125
Contribution of Learning Outcomes to Programme Outcomes
PÇ-1
PÇ-2
PÇ-3
PÇ-4
PÇ-5
PÇ-6
PÇ-7
PÇ-8
PÇ-9
PÇ-10
PÇ-11
OÇ-1
5
4
5
5
5
4
3
5
4
5
4
OÇ-2
5
4
5
5
5
5
3
5
5
5
5
OÇ-3
5
5
5
4
4
4
3
5
5
5
5
OÇ-4
5
5
5
5
5
5
3
5
5
5
5
OÇ-5
5
5
5
5
5
5
3
5
5
5
5
OÇ-6
5
5
5
4
5
5
3
5
5
5
5
OÇ-7
5
5
4
5
5
5
3
5
5
5
5
Adnan Menderes University - Information Package / Course Catalogue
2026