Information Package / Course Catalogue
Artificial Intelligence and Deep Learning
Course Code: EEE671
Course Type: Area Elective
Couse Group: Third Cycle (Doctorate Degree)
Education Language: English
Work Placement: N/A
Theory: 2
Prt.: 2
Credit: 3
Lab: 0
ECTS: 8
Objectives of the Course

To teach the students techniques based on Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) with practical applications; ; to demonstrate their importance in the EEE with preparing projects.to be able to do AI and DL applications; to be able to present work ; to gain the ability to understand articles and follow recent development in the field.

Course Content

Fundamental concepts (AI, DL, ML, etc.); Linear regression; Artificial Neural Network (ANN); AI; ML; Single and Multilayer Perceptron; Feed-forward; Convolutional, and Recurrent neural networks (FFNNs, CNNs, and RNNs); Python applications.

Name of Lecturer(s)
Learning Outcomes
1.To gain the knowledge and ability to apply the basic concepts, techniques, mathematics and software infrastructure of the AI and DL.
2.To be able to develop projects in the interdisciplinary fields related with modern EEE problems involving estimation, classification, clustering, and recognition.
3.To be able to follow and comprehend develop intelligent software; to understand how machines can learn; to be able to make useful and effective AI designs.
4.Being able to follow the recent development in the field; to be able to make presentations by preparing short seminars in the field.
5.To gain experience in understanding articles and recent developments in the field.
Recommended or Required Reading
1.Haykin, Simon, 1998, “Neural Networks: A Comprehensive Foundation (2nd Edition)”, Prentice-Hall, 1998.
2.Ethem Alpaydın, “Introduction to Machine Learning (Adaptıve Computation and Machıne Learning)”, MIT press, 2004.
3.Chris Bishop, Pattern Recognition and Machine Learning, Springer 2006.
4.Richard O. Duda, Peter E. Hart, and David Q. Stork, Pattern Classification, 2nd edition, Wiley, 2000.
5.Lecture notes, internet sources and scientific literature in the field
Weekly Detailed Course Contents
Week 1 - Theoretical & Practice
Introduction: Artificial intelligence (AI), machine learning (ML) and deep learning (DL) relationship
Week 2 - Theoretical & Practice
Machine learning and artificial neural networks
Week 3 - Theoretical & Practice
Multilayer perceptron (MLP) and training of neural networks
Week 4 - Theoretical & Practice
Deep neural networks, Python libraries and applications
Week 5 - Theoretical & Practice
Convolutional neural networks (CNNs)
Week 6 - Theoretical & Practice
CNN architectures: LeNet, AlexNet, GoogleNet, ResNet, fast R-CNN, etc.
Week 7 - Theoretical & Practice
Python applications of CNNs
Week 8 - Theoretical & Practice
Review - Midterm exam
Week 9 - Theoretical & Practice
Recurrent neural networks (RNN) and engineering applications
Week 10 - Theoretical & Practice
Training of RNNs
Week 11 - Theoretical & Practice
LSTM (Long Short-Term Memory)
Week 12 - Theoretical & Practice
Python applications (handwriting recognition, license plate recognition, voice recognition, translation, stock market and exchange rate prediction, image processing, etc.)
Week 13 - Theoretical & Practice
Python applications
Week 14 - Theoretical & Practice
Project presentations
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
PÇ-8
PÇ-9
PÇ-10
PÇ-11
PÇ-12
OÇ-1
4
4
5
4
4
4
4
5
4
5
5
4
OÇ-2
4
5
4
5
5
4
5
4
5
5
4
4
OÇ-3
4
5
5
5
5
4
5
5
5
4
5
4
OÇ-4
5
5
5
4
4
5
5
5
5
4
5
5
OÇ-5
5
5
5
4
5
5
5
5
5
5
5
5
Adnan Menderes University - Information Package / Course Catalogue
2026