Electrical and Electronics Engineering

Course Code	Course Name	Year	Period	Semester	T+A+L	Credit	ECTS
05171709	Introduction to Artificial Neural Networks	4	Autumn	7	3+0+0	5	5

Course Type	Elective
Course Cycle	Bachelor's (First Cycle) (TQF-HE: Level 6 / QF-EHEA: Level 1 / EQF-LLL: Level 6)
Course Language	Turkish
Methods and Techniques	-
Mode of Delivery	Face to Face
Prerequisites	-
Coordinator	-
Instructor(s)	Asst. Prof. Muharrem Selim CAN
Instructor Assistant(s)	-

Basic Vocational Courses
Specialization / Field Courses
Support Courses	X
Transferable Skills Courses
Humanities, Communication and Management Skills Courses

Relationship Levels
Lowest	Low	Medium	High	Highest
1	2	3	4	5

#	Program Learning Outcomes	Level
P1	Solid knowledge base in mathematics, natural sciences, and engineering-related subjects, along with the ability to solve complex engineering problems using this knowledge.	4
P2	Ability to identify, describe, mathematically express, and solve challenging engineering problems; the capability to select and utilize appropriate analysis and modeling techniques for this purpose.	5
P3	Ability to design a complex system, process, device, or product to meet specific requirements within real-world constraints and conditions; using current design techniques to achieve this goal.	5
P4	Ability to develop, prefer, and utilize current techniques and tools for analyzing and solving complex problems in engineering applications; proficiency in effectively utilizing information technologies.	5

Upon the successful completion of this course, students will be able to:
No	Learning Outcomes	Outcome Relationship	Measurement Method **
O1	Understanding the principles of Artificial Neural Networks and learning their differences from traditional programs.	P.1.83	1
O2	Understanding and learning the basic structure of Artificial Neural Networks and various network structures.	P.2.71	1
O3	Learning simple Artificial Neural Networks training methods	P.3.18	1
O4	Learning how to prepare and run an Artificial Neural Networks project	P.4.32	1
** Written Exam: 1, Oral Exam: 2, Homework: 3, Lab./Exam: 4, Seminar/Presentation: 5, Term Paper: 6, Application: 7

Week	Topics
1	Study of how a human nerve works.
2	Various neural models (electronic, mathematical) etc.
3	Examining Artificial Neural Network (ANN) models.
4	Classification of various ANNs
5	ANN Training methods
6	Single and multi-layer ANN models
7	Backpropagation algorithm
8	Counter propagation algorithm, other algorithms.
9	Midterm
10	Hoppfield ANNs. A simple ANN design on the subject. Homework.
11	Sample ANN applications. Homework control.
12	Sample ANN applications. Homework control.
13	Sample ANN applications. Homework control.
14	Assignment presentation and Final exam Also

Resources

E.Öztemel, Yapay Sinir Ağları, PapatyaBilim, 2016.

In-Term Studies	Quantity	Percentage
Attendance	-	-
Laboratory	-	-
Practice	-	-
Homework	-	-
Presentation	-	-
Projects	-	-
Quiz	-	-
Listening	-	-
Midterms	1	40 (%)
Final Exam	1	60 (%)
Total		100 (%)

	Quantity	Duration	Total Work Load
Course Week Number and Time	14	3	42
Out-of-Class Study Time (Pre-study, Library, Reinforcement)	14	4	56
Midterms	1	3	3
Quiz	0	0	0
Homework	0	0	0
Practice	0	0	0
Laboratory	0	0	0
Project	0	0	0
Workshop	0	0	0
Presentation/Seminar Preparation	0	0	0
Fieldwork	0	0	0
Final Exam	1	3	3
Other	14	4	56
Total Work Load:			160
Total Work Load / 30			5,33
Course ECTS Credits:			5

Relationship Levels
Lowest	Low	Medium	High	Highest
1	2	3	4	5

#	Learning Outcomes	P1	P2	P3	P4
O1	Understanding the principles of Artificial Neural Networks and learning their differences from traditional programs.	2	-	-	-
O2	Understanding and learning the basic structure of Artificial Neural Networks and various network structures.	-	4	-	-
O3	Learning simple Artificial Neural Networks training methods	-	-	3	-
O4	Learning how to prepare and run an Artificial Neural Networks project	-	-	-	3