Türkçe | English
FACULTY of ENGINEERING / DEPARTMENT of COMPUTER ENGINEERING
(30%) English
Course Catalog
https://www.ktu.edu.tr/bilgisayar
Phone: +90 0462 377 2080
MF
FACULTY of ENGINEERING / DEPARTMENT of COMPUTER ENGINEERING / (30%) English
Katalog Ana Sayfa
  Katalog Ana Sayfa  KTÜ Ana Sayfa   Katalog Ana Sayfa
 
 
BIL3027Artificial neural networks3+0+0ECTS:4
Year / SemesterFall Semester
Level of CourseFirst Cycle
Status Elective
DepartmentDEPARTMENT of COMPUTER ENGINEERING
Prerequisites and co-requisitesNone
Mode of Delivery
Contact Hours14 weeks - 3 hours of lectures per week
LecturerProf. Dr. Murat EKİNCİ
Co-LecturerNone
Language of instructionTurkish
Professional practise ( internship ) None
 
The aim of the course:
The course intends to teach the students for the principles of Artificial Neural Networks (ANN) . The fundamentals of artificial neural systems theory, algorithms for information acquisitions and retrieval, examples of applications, implementation issues are also included.
 
Learning OutcomesCTPOTOA
Upon successful completion of the course, the students will be able to :
LO - 1 : understand what ANN is and how it works1.2 - 1.3 - 2.1 - 5.31, 3
LO - 2 : design and train feedforward networks1.2 - 1.3 - 2.1 - 5.31, 3
LO - 3 : design and train feedback networks1.2 - 1.3 - 2.1 - 5.31, 3
LO - 4 : gain knowledge on how multi-layer ANN's work and are trained1.2 - 1.3 - 2.1 - 5.31, 3
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
Introduction; Fundemantal Concepts and Models of Artificial Neural Network; Learning Rules; Classification Models: Discriminant Functions, Linear Machine; Nonparametric Training Concepts; Training and classification using Discrete; Perceptron; Single Layer single-level Continous Perceptron Networks; Single Layer Multi-Level Continous Networks; Delta Learning Rule for Multiperceptron Layer; Generalized Delta Rule for Fully Connected Networks (FFCN); Learning Factors in FCN; Single-Layer Feedback Networks, Unsupervised Learning and Clusters; Convolutional Neural Networks (CNN); CNN Arhitectures: ALexNet, VGGNet, ResNet, YOLO
 
Course Syllabus
 WeekSubjectRelated Notes / Files
 Week 1Artificial neural systems: Introduction
 Week 2Fundemantal Concepts and Models of Artificial Neural Network
 Week 3Neural Network Learning Rules
 Week 4Classification Models: Discriminant Functions, Linear Machine.
 Week 5Nonparametric Training Concepts
 Week 6Training and classification with single layer Discrete Perceptron
 Week 7Single Layer Continous Perceptron Networks for classification and Regression
 Week 8Linearly Nonseparable Pattern Classification
 Week 9Mid-term exam
 Week 10Delta Learning Rule for Multiperceptron Layers
 Week 11Generalized Delta Rule (Erreor Back Propagation) for Fully Connected Networks (FCN)
 Week 12Learning Factors in Multi-Layer Networks
 Week 13Single-Layer Feedback Networks, Unsupervised Learning and Clusters
 Week 14Evrişimsel Sinir Ağları (ESA)
 Week 15CNN Arhitectures for classification, detection, segmentation: ALexNet, VGGNet, ResNet, YOLO, U-Net
 Week 16End-of-term exam
 
Textbook / Material
1Zurada, M., J., 1992, Introduction to Artificial Neural Systems, West Publishing Company, 825 p.
 
Recommended Reading
1Cichocki, A., Unbehauen, R., 1993, Neural Networks for Optization and Signal Processing, John Wiley, 526 p.
 
Method of Assessment
Type of assessmentWeek NoDate

Duration (hours)Weight (%)
Mid-term exam 9 25/11/2020 2 30
Project 15 29/12/2020 2 20
End-of-term exam 16 25/01/2021 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 1 14 14
Arasınav için hazırlık 10 1 10
Arasınav 2 1 2
Ödev 2 8 16
Dönem sonu sınavı için hazırlık 11 1 11
Dönem sonu sınavı 2 1 2
Total work load97