Course Details

Return to Classes
Course Information
SemesterCourse Unit CodeCourse Unit TitleT+P+LCreditNumber of ECTS CreditsLast Updated Date
1ECE560ARTIFICIAL NEURAL NETWORKS3+0+037,514.05.2025

 
Course Details
Language of Instruction English
Level of Course Unit Doctorate's Degree
Department / Program ELECTRICAL AND COMPUTER ENGINEERING
Type of Program Formal Education
Type of Course Unit Elective
Course Delivery Method Face To Face
Objectives of the Course O1. Develop knowledge for the fundamentals of neural networks
O2. Learn the techniques used for developing neural network models
O3. Develop skills for practical aspects of neural networks
O4. Apply the concepts learned to a real problem
Course Content This course provides an introduction to neural networks. It covers perceptrons, single and multi-layer networks, network training, regularization, and ensembles. Mathematical principles will be explained to provide a solid foundation for neural networks. Methods will be implemented by a software and applied on various machine learning problems.
Course Methods and Techniques In the course, theoretical explanations are supported by interactive presentations and sample solutions to explain mathematical foundations.

Students perform applications with Python-based software tools to experience the applicability of neural network structures.

The information learned is reinforced with project-based studies on selected real-world machine learning problems.
Prerequisites and co-requisities None
Course Coordinator None
Name of Lecturers Associate Prof.Dr. Zafer Aydın Avesi zafer.aydin@agu.edu.tr
Assistants None
Work Placement(s) No

Recommended or Required Reading
Resources 1. Neural Networks and Learning Machines, 3rd edition, Simon Haykin, 2009. 2. Neural Networks for Pattern Recognition, Christopher Bishop, 1995. 3. Pattern Recognition and Machine Learning, Christopher Bishop, 2006.
Course Notes 1. Neural Networks and Learning Machines, 3rd edition, Simon Haykin, 2009.
2. Neural Networks for Pattern Recognition, Christopher Bishop, 1995.
3. Pattern Recognition and Machine Learning, Christopher Bishop, 2006.
Documents Will be shared on Canvas
Assignments Will be shared on Canvas
Exams Will be shared on Canvas

Course Category
Mathematics and Basic Sciences %20
Engineering %20
Engineering Design %20
Social Sciences %0
Education %0
Science %20
Health %0
Field %20

Planned Learning Activities and Teaching Methods
Activities are given in detail in the section of "Assessment Methods and Criteria" and "Workload Calculation"

Assessment Methods and Criteria
In-Term Studies Quantity Percentage
Yarıl yılSonu Sınavı/Dönem Projesinin Başarı Notuna Katkısı 1 % 20
Quiz/Küçük Sınav 1 % 10
Ödev 1 % 25
Proje/Çizim 1 % 25
Final examination 1 % 20
Total
5
% 100

 
ECTS Allocated Based on Student Workload
Activities Quantity Duration Total Work Load
Proje 1 88 88
Senkron Ders 14 3 42
Ders Dışı Ara Sınav 1 20 20
Final Sınavı 1 30 30
Total Work Load   Number of ECTS Credits 7,5 180

 
Course Learning Outcomes: Upon the successful completion of this course, students will be able to:
NoLearning Outcomes
1 Explain the mathematical and algorithmic principles of neural networks
2 Solve a machine learning problem by applying the appropriate neural network methodologies
3 Implement neural network methods using an appropriate software
4 Apply a neural network method to a real problem

 
Weekly Detailed Course Contents
WeekTopicsStudy MaterialsMaterials
1 Introduction: what is a neural network, the human brain, models of a neuron, neural networks viewed as directed graphs Activity: reading Haykin’s book chapter introduction
2 Introduction: network architectures, knowledge representation, learning processes, learning tasks Activity: quiz 1, Reading Haykin’s book chapter introduction
3 Single layer networks: Rosenblat’s perceptron Activity: homework 1, reading Haykin’s book chapter 1, Bishop’s NNPR book chapter 3
4 Multi-layer perceptron: feed-forward network functions, weight space symmetries, network training Activity: homework 2, reading Bishop’s PRML book Chapter 5, Bishop’s NNPR book chapter 4
5 Error functions and their derivatives Activity: quiz 2, reading Bishop’s PRML book Chapter 5, Bishop’s NNPR book chapter 6
6 Network training: gradient descent algorithm, error backpropagation Activity: homework 3, reading Bishop’s PRML book Chapter 5, Bishop’s NNPR book chapter 4
7 Network training: gradient descent algorithm, error backpropagation Activity: quiz 3, reading Bishop’s PRML book Chapter 5, Bishop’s NNPR book chapter 4
8 Semester break
9 Midterm exam
10 Network training: Hessian matrix Activity: homework 4, reading Bishop’s PRML book Chapter 5, Bishop’s NNPR book chapter 4
11 Network training, conjugate gradient, line search Activity: quiz 4, project, reading Bishop’s NNPR book chapter 7
12 Network training: Quasi-Newton, Levenberg-Marquardt, RMSprop, Adam Activity: homework 5, project, reading Bishop’s NNPR book chapter 7
13 Regularization: L1 and L2 norm, early stopping, tangent propagation, dropout Activity: quiz 5, homework 6, project, reading Bishop’s PRML book Chapter 5
14 Combining neural networks Activity: homework 7, project, reading Bishop’s NNPR book chapter 9

 
Recommended Optional Programme Components
Veri yok
Contribution of Learning Outcomes to Programme Outcomes
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11
All 3 5 4 4 4 3 3 1 2 1 1
C1 3 5 3 3 3 1 3 1 1 1 1
C2 3 5 5 5 5 3 3 1 3 1 1
C3 1 5 3 3 3 3 3 1 2 1 1
C4 3 5 5 5 5 5 3 1 3 1 1

  Contribution: 1: Very Slight 2:Slight 3:Moderate 4:Significant 5:Very Significant

  
  https://sis.agu.edu.tr/oibs/bologna/progCourseDetails.aspx?curCourse=77883&lang=en
Return to Classes