Türkçe | English
FACULTY of SCIENCE / DEPARTMENT of STATISTICS and COMPUTER SCIENCES

Course Catalog
http://www.ktu.edu.tr/isbb
Phone: +90 0462 3773112
FENF
FACULTY of SCIENCE / DEPARTMENT of STATISTICS and COMPUTER SCIENCES /
Katalog Ana Sayfa
  Katalog Ana Sayfa  KTÜ Ana Sayfa   Katalog Ana Sayfa
 
 

IST4024Artificial neural networks4+0+0ECTS:6
Year / SemesterSpring Semester
Level of CourseFirst Cycle
Status Elective
DepartmentDEPARTMENT of STATISTICS and COMPUTER SCIENCES
Prerequisites and co-requisitesNone
Mode of Delivery
Contact Hours14 weeks - 4 hours of lectures per week
LecturerDoç. Dr. Orhan KESEMEN
Co-Lecturer
Language of instructionTurkish
Professional practise ( internship ) None
 
The aim of the course:
The following topics will be included in the course: The main neural network architectures and learning algorithms, perceptrons and the LMS algorithm, back propagation learning, radial basis function networks, support vector machines, Kohonen?s self organizing feature maps, Hopfield networks, artificial neural networks for signal processing, pattern recognition and control.
 
Learning OutcomesCTPOTOA
Upon successful completion of the course, the students will be able to :
LO - 1 : Describe basic artificial neural network models,5,91,
LO - 2 : Use the most common ANN architectures and their learning algorithms for a specific application,5,91,
LO - 3 : Explain the principles of supervised and unsupervised learning, and generalization ability,5,91,
LO - 4 : Evaluate the practical considerations in applying ANNs to real classification, pattern recognition, signal processing and control problems,5,91,
LO - 5 : Implement basic ANN models and algorithms using Matlab and its Neural Network Toolbox.5,91,
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
This course will introduce the fundamental principles and algorithms of Artificial Neural Network (ANN) systems. The course will cover many subjects including basic neuron model, simple perceptron, adaptive linear element, Least Mean Square (LMS) algorithm, Multi Layer Perceptron (MLP), Back Propagation (BP) learning algorithm, Radial Basis Function (RBF) networks, Self Organizing Maps (SOM) and Learning Vector Quantization (LVQ), Support Vector Machines (SVMs), Continuous time and discrete time Hopfield networks, classification techniques, pattern recognition, signal processing and control applications.
 
Course Syllabus
 WeekSubjectRelated Notes / Files
 Week 1Biological motivation. Historical remarks on artificial neural networks. Applications of artificial neural networks. A taxonomy of artificial neural network models and learning algorithms.
 Week 2General artificial neuron model. Discretevalued perceptron model, threshold logic and their limitations. Discretetime (dynamical) Hopfield networks. Hebb?s rule. Connection wieght matrix as an outer product of memory patterns.
 Week 3Supervised learning. Perceptron learning algorithm. Adaptive linear element. Supervised learning as output error minimization problem. Gradient descent algorithm for minimization. Least mean square rule.
 Week 4Single layer, continuous valued perceptron. Nonlinear (sigmoidal) activation function. Delta rule. Batch mode and pattern mode gradient descent algorithms. Convergence conditions for deterministic and stochastic gradient descent algorithms.
 Week 5Multi layer perceptron as universal approximator. Function representation and approximation problems. Backpropagation Learning. Local minima problem. Overtraining.
 Week 6Batch and pattern mode training. Training set versus test set. Overfitting problem. General practices for network training and testing. Signal processing and pattern recognition applications of multilayer perceptrons.
 Week 7Radial Basis Function (RBF) network. Backpropagation learning for determining linear weights, centers and widths parameters of RBF networks. Random selection of centers. Input versus input-output clustering for center and width determination. Regularization theory, mixture of Gaussian (conditional probability density function) model and neurofuzzy connections of RBF networks.
 Week 8Parametric versus nonparametric methods for data representation. Unsupervised learning as a vector quantization problem. Competitive networks. Winner takes all networks. Kohonen?s self organizing feature map. Clustering.
 Week 9Mid-term exam
 Week 10Signal processing applications of artificial neural networks. Principal component analysis. Data compression and reduction. Image and 1D signal compression and transformation applications of artificial neural networks.
 Week 11Pattern recognition applications of artificial neural networks. Artificial neural networks for feature extraction. Nonlinear feature mapping. Data fusion. Artificial neural networks as classifiers. Image and speech recognition applications.
 Week 12Implementation of artificial neural networks models and associated learning algorithms for signal processing, pattern recognition and control in MATLAB numerical software environment.
 Week 13Implementation of artificial neural networks models and associated learning algorithms for signal processing, pattern recognition and control in MATLAB numerical software environment.
 Week 14Cumulative review of artificial neural networks models, learning algorithms and their applications.
 Week 15Cumulative review of artificial neural networks models, learning algorithms and their applications.
 Week 16End-term exam
 
Textbook / Material
1Eğrioğlu, Erol; Yolcu Ufuk; Baş Eren; 2020; Yapay Sinir Ağları
 
Recommended Reading
 
Method of Assessment
Type of assessmentWeek NoDate

Duration (hours)Weight (%)
Mid-term exam 9 23/11/2021 2 50
End-of-term exam 16 18/01/2022 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 4 14 56
Sınıf dışı çalışma 3 14 42
Arasınav için hazırlık 10 1 10
Arasınav 2 1 2
Dönem sonu sınavı için hazırlık 17 1 17
Dönem sonu sınavı 2 1 2
Total work load129