Course Information
SemesterCourse Unit CodeCourse Unit TitleT+P+LCreditNumber of ECTS CreditsLast Updated Date
5BBM476ARTİFİCİAL NEURAL NETWORKS3+0+03606.09.2024

 
Course Details
Language of Instruction English
Level of Course Unit Bachelor's Degree
Department / Program COMPUTER ENGINEERING
Type of Program Formal Education
Type of Course Unit Elective
Course Delivery Method Face To Face
Objectives of the Course The aims of this course are to teach the black box models based on numerical data or experience, to teach the notion of adaptive systems, to teach -some of- the neural approaches in intelligent systems research, to use a CAD software and CAD based simulation.
Course Content Historical perspective
Continuous and discrete system models
Neuron and its analytic model
Hopfield neural network
Perceptron learning algorithms
Multilayer perceptron
Error backpropagation algorithm and its problems
Radial basis function neural networks
Dynamical neural networks
Feedback neural networks
Second order training algorithms
Derivative free optimzation
Particle swarm optimization algorithm
Applications of neural networks
Reinforcement learning
Unsupervised learning
Course Methods and Techniques Lecture, Problem Solving
Prerequisites and co-requisities ( BBM102 ) and ( BBM104 )
Course Coordinator Prof. Mehmet Önder Efe
Name of Lecturers None
Assistants None
Work Placement(s) No

Recommended or Required Reading
Resources Haykin, S., Neural Networks, Macmillan College Printing Company, New Jersey, 1994.
Bishop, C. M., Neural Networks for Pattern Recognition, Oxford University Press, 1995.


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
Assignment 2 % 20
Preparation for Midterm Exam 1 % 40
Total
3
% 60

 
ECTS Allocated Based on Student Workload
Activities Quantity Duration Total Work Load
Course Duration 14 3 42
Hours for off-the-c.r.stud 14 5 70
Assignments 2 5 10
Mid-terms 1 20 20
General Exam Preparation 1 38 38
Total Work Load   Number of ECTS Credits 6 180

 
Course Learning Outcomes: Upon the successful completion of this course, students will be able to:
NoLearning Outcomes
1 Understand the types of neural nets and the principles of how they work
2 Understand the principles of adaptive neural systems
3 Understand the notion of learning and the ways to obtain it
4 Gain the capablity of CAD based solutions
5 Gain the capabilities of conducting research, reporting the results and presenting the results

 
Weekly Detailed Course Contents
WeekTopicsStudy MaterialsMaterials
1 Historical perspective. Continuous and discrete system models.
2 Neuron and its analytic model.
3 Hopfield neural networks.
4 Perceptron learning algorithms.
5 Multilayer perceptron. Error backpropagation algorithm and its problems.
6 Radial basis function neural networks.
7 Dynamical neural networks.
8 Midterm
9 Feedback neural networks
10 Second order training algorithms
11 Derivative free optimzation
12 Particle swarm optimization algorithm
13 Applications of neural networks
14 Reinforcement learning. Unsupervised learning
15 Preparation to final exam
16 Final Exam

 
Contribution of Learning Outcomes to Programme Outcomes
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 P12
All 3 4 5 2 1 1 2 2 1 1 1
C1
C2
C3
C4
C5

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

  
  https://bilsis.hacettepe.edu.tr/oibs/bologna/progCourseDetails.aspx?curCourse=2687596&lang=en