Türkçe | English
GRADUATE INSTITUTE of NATURAL and APPLIED SCIENCES / DEPARTMENT of GEOMATICS ENGINEERING
Doctorate
Course Catalog
http://www.fbe.ktu.edu.tr
Phone: +90 0462 04623772707
FBE
GRADUATE INSTITUTE of NATURAL and APPLIED SCIENCES / DEPARTMENT of GEOMATICS ENGINEERING / Doctorate
Katalog Ana Sayfa
  Katalog Ana Sayfa  KTÜ Ana Sayfa   Katalog Ana Sayfa
 
 
JDZL7370ANN Applications in GeomatiC Eng.3+0+0ECTS:7.5
Year / SemesterSpring Semester
Level of CourseThird Cycle
Status Elective
DepartmentDEPARTMENT of GEOMATICS ENGINEERING
Prerequisites and co-requisitesNone
Mode of Delivery
Contact Hours14 weeks - 3 hours of lectures per week
LecturerDr. Öğr. Üyesi Leyla ÇAKIR
Co-LecturerNone
Language of instructionTurkish
Professional practise ( internship ) None
 
The aim of the course:
To have knowledge of analyze and design in the Artificial neural networks (ANN)
 
Programme OutcomesCTPOTOA
Upon successful completion of the course, the students will be able to :
PO - 1 : Learn the basic concepts with ANN11
PO - 2 : Learn the differences in the ANN structures1,21
PO - 3 : See advantages/disadvantages of the ANN as compared with classical methods2,33
PO - 4 : Use ANN efficiently to solve surveying engineering problems2,5,73
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), PO : Learning Outcome

 
Contents of the Course
Introduction to Artificial Neural Networks (ANN),the historical development of the ANN, Biological and artificial neural cell properties, ANN features, ANN classification, The learning algorithms and basic learning rules used in ANN, Multilayer perceptron networks, Various artificial neural networks.
 
Course Syllabus
 WeekSubjectRelated Notes / Files
 Week 1Introduction
 Week 2Artificial Neural Networks (ANN), general usage areas of ANNs
 Week 3The historical development of ANNs
 Week 4Features of ANNs
 Week 5Classification of ANNs
 Week 6The learning algorithms used in the ANN
 Week 7ANN learning rules
 Week 8Single-layer neural network
 Week 9Mid-term exam
 Week 10Multilayer perceptron networks
 Week 11ANN design
 Week 12Radial basis function neural networks
 Week 13Generalized regression neural networks
 Week 14Project presentations
 Week 15Project presentations
 Week 16End-of-term exam
 
Textbook / Material
1Haykin S. 1999; Neural Networks: A Comprehensive Foundation, Prentice Hall
2Haykin S. 1999; Neural Networks: A Comprehensive Foundation, Prentice Hall
3Bishop, C. M. 1995; Neural Networks for Pattern Recognition, Oxford University Press
4Bishop, C. M. 1995; Neural Networks for Pattern Recognition, Oxford University Press
 
Recommended Reading
1Zurada, M. J. 1992; Introduction to Artificial Neural Systems, West Publishing Company
2Zurada, M. J. 1992; Introduction to Artificial Neural Systems, West Publishing Company
 
Method of Assessment
Type of assessmentWeek NoDate

Duration (hours)Weight (%)
Mid-term exam 9 2 30
Project 14,15 20
Practice 12,13
End-of-term exam 16 2 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 4 12 48
Laboratuar çalışması 2 2 4
Arasınav için hazırlık 2 7 14
Arasınav 2 1 2
Uygulama 2 2 4
Ödev 2 2 4
Proje 2 2 4
Dönem sonu sınavı için hazırlık 2 14 28
Dönem sonu sınavı 3 1 3
Total work load153