Course Information

Course Title	Code	Semester	L+U Hour	Credits	ECTS
ARTIFICIAL INTELLIGENCE WITH APPLICATIONS TO AEROSPACE SYSTEMS	803400815151		3 + 0	3.0	10.0

Prerequisites

None

Language of Instruction	English
Course Level	Graduate Degree
Course Type	Elective
Mode of delivery
Course Coordinator
Instructors	Asım Egemen YILMAZ
Assistants
Goals	The goal of this course is to introduce artificial intelligence with applications specific to the aerospace sector.
Course Content	"The course will focus on introducing the main concepts of AI from ground zero covering the main building of machine learning starting from data processing all the way to deep learning and reinforcement learning. The course will utilize data and concepts stemming from real life machine learning projects undertaken at ITU Aerospace Research Center. Examples and applications include digital-twin modeling of wide body aircraft using neural networks and agile maneuvering flight planning tools using machine learning methods. By the end of the course, we expect the students to develope hands-on skills on ML and to demonstrate these skills on projects of interest."
Learning Outcomes	1) Knows data processing and learning methods 2) Knows aerospace systems 3) Applies data processing and learning methods tp aerospace systems

Week	Topics	Teaching and Learning Methods and Techniques	Study Materials
1. Week	Introduction to Aerospace Systems	Lecture	Homework
2. Week	Introduction to Machine Learning Principles	Lecture	Homework
3. Week	Learning From Data, Data, Preprocessing, Data Visualization, Feature Extraction	Lecture	Homework
4. Week	Supervised Learning Algorithms	Lecture	Homework
5. Week	Unsupervised Learning Algorithms	Lecture	Homework
6. Week	Machine Learning Model Training and Testing	Lecture	Homework
7. Week	Introduction to Neural Networks	Lecture	Homework
8. Week	Introduction to Deep Neural Networks, Model Training and Evaluation Techniques	Lecture	Homework
9. Week	Deep L earning Training Tips and Tricks, CNN, RNN, GAN Architectures	Lecture	Homework
10. Week	Deep Learning Aviation Application 1: System Identification and Digital Twin Models with Deep Neural Networks	Lecture	Homework
11. Week	Deep Learning Aviation Application 2: Anomaly Detection with Deep Neural Networks: Deep Autoencoders	Lecture	Homework
12. Week	Deep Learning Aviation Application 3: Analytic Function Approximation with Deep Neural Networks : Deep FF Networks	Lecture	Homework
13. Week	Introduction to Reinforcement Learning	Lecture	Homework
14. Week	Reinforcement Learning Application for Aviation : Deep Q Networks	Lecture	Homework

Recommended Sources

I. Goodfellow, Y. Bengio and A. Courville, Deep Learning, 2016, MIT Press

K.P. Murphy, Machine Learning: A Probabilistic Perspective, 2012, MIT Press

R. S. Sutton, A. G. Barto, Reinforcement Learning: An Introduction, 1998, The MIT Press

*DK = Course's Contrubution.

	0	1	2	3	4	5
Level of contribution	None	Very Low	Low	Fair	High	Very High

Event	Quantity	Duration (Hour)	Total Workload (Hour)
Course Duration (Total weeks*Hours per week)	14	3	42
Work Hour outside Classroom (Preparation, strengthening)	14	9	126
Homework	2	20	40
Presentation (Including Preparation Time)	1	20	20
Project (Including Preparation and presentation Time)	1	1	1
Report (Including Preparation and presentation Time)	1	1	1
Midterm Exam	1	1	1
Time to prepare for Midterm Exam	1	20	20
Final Exam	1	1	1
Time to prepare for Final Exam	1	40	40
Total Workload
Total Workload / 30 (s)
ECTS Credit of the Course			30