Türkçe | English
FACULTY of ENGINEERING / DEPARTMENT of INDUSTRIAL ENGINEERING

Course Catalog
http://www.ktu.edu.tr/endustri
Phone: +90 0462 3773824
MF
FACULTY of ENGINEERING / DEPARTMENT of INDUSTRIAL ENGINEERING /
Katalog Ana Sayfa
  Katalog Ana Sayfa  KTÜ Ana Sayfa   Katalog Ana Sayfa
 
 
END4027Artificial Neural Networks3+0+0ECTS:5
Year / SemesterFall Semester
Level of CourseFirst Cycle
Status Elective
DepartmentDEPARTMENT of INDUSTRIAL ENGINEERING
Prerequisites and co-requisitesNone
Mode of Delivery
Contact Hours14 weeks - 3 hours of lectures per week
LecturerProf. Dr. Şükrü ÖZŞAHİN
Co-Lecturer
Language of instructionTurkish
Professional practise ( internship ) None
 
The aim of the course:
The goal of this course is to teach the fundamental principles and algorithms of Artificial Neural Network (ANN) systems for modeling and solving engineering problems.
 
Learning OutcomesCTPOTOA
Upon successful completion of the course, the students will be able to :
LO - 1 : Describe basic artificial neural network models3,41,6
LO - 2 : Use the most common ANN architectures and their learning algorithms for a specific application3,41,5,6
LO - 3 : Implement basic ANN models and algorithms using Matlab and its Neural Network Toolbox3,41,3,6
CTPO : Contribution to programme outcomes, TOA :Type of assessment (1: written exam, 2: Oral exam, 3: Homework assignment, 4: Laboratory exercise/exam, 5: Seminar / presentation, 6: Term paper), LO : Learning Outcome

 
Contents of the Course
Artificial intelligence and machine learning. fundamentals of ANN, neural cell models, Multi-Layer Perception network (MLP), backpropagation learning, supervised learning, unsupervised learning, reinforcement learning, applications of artificial neural networks, project presentation
 
Course Syllabus
 WeekSubjectRelated Notes / Files
 Week 1Introduction to artificial intelligence and machine learning
 Week 2Introduction to artificial neural networks, fundamentals of ANN
 Week 3Biological and artificial nerve cells, neural cell models
 Week 4Supervised learning: Perceptron learning algorithm
 Week 5Basic network topologies and Multi-layer Perceptron network (MLP)
 Week 6Backpropagation learning
 Week 7Radial Basis Function (RBF) network.
 Week 8Unsupervised learning: Adaptive Resonance Theory (ART), Reinforcement learning: Learning Vector Quantization (LVQ), Self-Organizing Maps (SOM)
 Week 9Midterm exam
 Week 10Applications of artificial neural networks
 Week 11Industrial engineering applications with ANN
 Week 12Forecasting with ANN
 Week 13Implementation of artificial neural networks models and associated learning algorithms in MATLAB numerical software environment
 Week 14ANN software and applications
 Week 15Project presentation
 Week 16Final exam
 
Textbook / Material
1Aggarwal, Charu C. 2018; Neural Networks and Deep Learning: A Textbook, Springer, ISBN: 978-3319944623.
2Prof. Dr. Çetin Elmas, 2007, "Yapay Zeka Uygulamaları", Seçkin Yayıncılık, 425 s. Prof. Dr. Ercan Öztemel, 2003, "Yapay Sinir Ağları", Papatya Yayıncılık, 238s.
3Haykin, Simon. 2004; Neural Networks: A Comprehensive Foundation, Prentice Hall, 2nd Edition, ISBN: 978-0132733502.
 
Recommended Reading
1Vasif Nabiyev , Yapay Zeka: Problemler, Yöntemler, Algoritmalar, 2. baskı, 764 s., Seçkin, Ankara, 2005.
2Şeref Sağıroğlu, Erkan Beşdok, Mehmet Erler, 2003, "Mühendislikte Yapay Zeka Uygulamaları - I : Yapay Sinir Ağları", Ufuk Yayıncılık, 426s.
 
Method of Assessment
Type of assessmentWeek NoDate

Duration (hours)Weight (%)
Mid-term exam 9 1.5 20
Project 14 1.5 15
Homework/Assignment/Term-paper 8 1.5 15
End-of-term exam 16 1.5 50
 
Student Work Load and its Distribution
Type of workDuration (hours pw)

No of weeks / Number of activity

Hours in total per term
Yüz yüze eğitim 3 14 42
Sınıf dışı çalışma 3 12 36
Arasınav için hazırlık 8 1 8
Arasınav 1.5 1 1.5
Ödev 3 2 6
Proje 6 1 6
Dönem sonu sınavı için hazırlık 9 1 9
Dönem sonu sınavı 1.5 1 1.5
Total work load110