Türkçe | English
FACULTY of ARCHITECTURE / DEPARTMENT of INTERIOR ARCHITECTURE
Undergraduate
Course Catalog
http://www.icmimarlik.ktu.edu.tr
Phone: +90 0462 3772695
MİMF
FACULTY of ARCHITECTURE / DEPARTMENT of INTERIOR ARCHITECTURE / Undergraduate
Katalog Ana Sayfa
  Katalog Ana Sayfa  KTÜ Ana Sayfa   Katalog Ana Sayfa
 
 
SEC 415Artificial Neural Networks3+0+0ECTS:5
Year / SemesterFall Semester
Level of CourseFirst Cycle
Status Elective
DepartmentDEPARTMENT of COMPUTER ENGINEERING
Prerequisites and co-requisitesNone
Mode of DeliveryFace to face
Contact Hours14 weeks - 3 hours of lectures per week
Lecturer--
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 works1,3,4,5,81, 3
LO - 2 : design and train feedforward networks1,3,4,5,81, 3
LO - 3 : design and train feedback networks1,3,4,5,81, 3
LO - 4 : gain knowledge on how multi-layer ANN's work and are trained1,3,4,5,81, 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
Fundmental concepts and Models of Artificial Neural Systems, Single-Layer Perceptron Classifiers, Multilayer Feedforward Networks, Single-Layer Feedback Networks, Associative Memories, Matching and Self-Organizing Networks, Application of Neural Algorithms and Systems.
 
Course Syllabus
 WeekSubjectRelated Notes / Files
 Week 1Artificial neural systems: Neural computation, History of ANS development
 Week 2Fundamental concepts and models of ANS: Biological neurons, Models of artificial neural network (ANN), Neural processing, Learning and adaptation
 Week 3Neural network learning rules. Single layer perceptron classifiers: Classification models, features, and decision regions, Discriminant functions, Lineer machine and minimum distance classification.
 Week 4Nonparametric training concept. Single layer continuous perceptron networks for lineerly separable classification. Examples.
 Week 5Multilayer feedforward networks: Lineerly nonseparable pattern classification, delta learning rulefor multiperceptron layer, Feedforward recall and error back-propagation training
 Week 6Learning factors
 Week 7Classifying and expert layered networks
 Week 8Single layer feedback networks: Basic concepts of dynamical systems,Mathematical foundations of discrete time Hopfield networks, Transient responce of continuous time networks
 Week 9Mid-term exam
 Week 10Relaxation modeling in single layer feedback networks, Example solution of optimization problems
 Week 11Associative memories
 Week 12Associative memories
 Week 13Matching and self organizing networks
 Week 14Matching and self organizing networks
 Week 15Applications of Neural algorithms and systems
 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 13/10/2012 2 30
Project 15 29/12/2012 2 20
End-of-term exam 16 05/01/2013 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
Kısa sınav 2 1 2
Dönem sonu sınavı için hazırlık 11 1 11
Dönem sonu sınavı 2 1 2
Total work load83