TR EN

ARTIFICIAL NEURAL NETWORKS PROGRAMME COURSE DESCRIPTION

Code Name of the Course Unit Semester In-Class Hours (T+P) Credit ECTS Credit
BIL422 ARTIFICIAL NEURAL NETWORKS 5 3 3 6

GENERAL INFORMATION

Language of Instruction : Turkish
Level of the Course Unit : BACHELOR'S DEGREE, TYY: + 6.Level, EQF-LLL: 6.Level, QF-EHEA: First Cycle
Type of the Course : Elective
Mode of Delivery of the Course Unit -
Coordinator of the Course Unit Assist.Prof. SERKAN GÖNEN
Instructor(s) of the Course Unit Lecturer KÜBRA ERDOĞAN
Course Prerequisite No

OBJECTIVES AND CONTENTS

Objectives of the Course Unit: The aim of this course is to provide comprehensive knowledge on the design, training, and testing of artificial neural networks.
Contents of the Course Unit: This course covers biological neurons and the brain, the model of a single neuron, neural networks, training algorithms, applications, benefits, weaknesses, and various uses of neural networks.

KEY LEARNING OUTCOMES OF THE COURSE UNIT (On successful completion of this course unit, students/learners will or will be able to)

Recognize and solve problems that can be addressed using artificial neural network algorithms.

WEEKLY COURSE CONTENTS AND STUDY MATERIALS FOR PRELIMINARY & FURTHER STUDY

Week Preparatory Topics(Subjects) Method
1 - Overview of Artificial Intelligence and Machine Learning -
2 - Introduction to Artificial Neural Networks -
3 - Structure and Basic Elements of Artificial Neural Networks -
4 - Early Artificial Neural Networks -
5 - Artificial Neural Network Model (Supervised Learning) Multilayer Perceptron -
6 - Artificial Neural Network Model (Supportive Learning) LVQ Model -
7 - Artificial Neural Network Model (Unsupervised Learning) Adaptive Resonance Theory (ART) Networks -
8 - MID-TERM EXAM -
9 - Recurrent Networks (Element Networks) and Other Artificial Neural Network Models -
10 - Hybrid Artificial Neural Networks -
11 - Hardware for Artificial Neural Networks -
12 - Overview of Applications of Artificial Neural Networks -
13 - Student Project Presentations -
14 - Student Project Presentations -
15 - ANN: General Overview -
16 - FINAL EXAM -
17 - FINAL EXAM -

SOURCE MATERIALS & RECOMMENDED READING

Laurene V. Fausett, “Fundamentals of Neural Networks: Architectures, Algorithms And Applications”, Prentice Hall.
Simon Haykin, “Neural Networks: A Comprehensive Foundation”, Prentice Hall
Paul E. Keller, Kevin L. Priddy, "Artificial Neural Networks: an Introduction", PHI, 2007
Ercan Öztemel, “Yapay Sinir Ağları”, Papatya Yayıncılık, 2012
Vasif Nabiyev, "Yapay Zeka", Seçkin Yayınları, 3. baskı 2010

ASSESSMENT

Assessment & Grading of In-Term Activities Number of Activities Degree of Contribution (%) Description Examination Method
Mid-Term Exam 1 30 Classical Exam
Homework Assessment 1 10
Short Exam 1 10
Final Exam 1 50 Classical Exam
TOTAL 4 100
Level of Contribution
0 1 2 3 4 5

CONTRIBUTION OF THE COURSE UNIT TO THE PROGRAMME LEARNING OUTCOMES

KNOWLEDGE

Theoretical

Programme Learning Outcomes Level of Contribution
0 1 2 3 4 5
1
Ability to identify, analyze, design, model and solve complex engineering problems based on engineering, science and mathematics fundamentals
5

KNOWLEDGE

Factual

Programme Learning Outcomes Level of Contribution
0 1 2 3 4 5
1
Ability to apply engineering design to produce solutions that meet specific needs, taking into account global, cultural, social, environmental and economic factors as well as public health, safety and well-being
4

SKILLS

Cognitive

Programme Learning Outcomes Level of Contribution
0 1 2 3 4 5
1
Ability to communicate effectively with various stakeholders
3

SKILLS

Practical

Programme Learning Outcomes Level of Contribution
0 1 2 3 4 5
1
The ability to recognize ethical and professional responsibilities in engineering and make informed decisions considering the impact of engineering solutions in their global, economic, environmental and social contexts
4

OCCUPATIONAL

Autonomy & Responsibility

Programme Learning Outcomes Level of Contribution
0 1 2 3 4 5
1
The ability to recognize ethical and professional responsibilities in engineering and make informed decisions considering the impact of engineering solutions in their global, economic, environmental and social contexts
4

OCCUPATIONAL

Learning to Learn

Programme Learning Outcomes Level of Contribution
0 1 2 3 4 5
1
Ability to acquire new knowledge and find ways to apply it when necessary, using appropriate learning strategies
3

OCCUPATIONAL

Communication & Social

Programme Learning Outcomes Level of Contribution
0 1 2 3 4 5
1
Ability to work effectively in a team where its members lead together, create a collaborative and inclusive environment, set goals, plan tasks, and meet goals
4

OCCUPATIONAL

Occupational and/or Vocational

Programme Learning Outcomes Level of Contribution
0 1 2 3 4 5
1
Ability to design and conduct appropriate experiments, analyze and interpret data, and apply engineering principles to draw conclusions
3

WORKLOAD & ECTS CREDITS OF THE COURSE UNIT

Workload for Learning & Teaching Activities

Type of the Learning Activites Learning Activities (# of week) Duration (hours, h) Workload (h)
Lecture & In-Class Activities 14 3 42
Preliminary & Further Study 14 3 42
Land Surveying 0 0 0
Group Work 0 0 0
Laboratory 0 0 0
Reading 0 0 0
Assignment (Homework) 0 0 0
Project Work 0 0 0
Seminar 0 0 0
Internship 0 0 0
Technical Visit 0 0 0
Web Based Learning 0 0 0
Implementation/Application/Practice 0 0 0
Practice at a workplace 0 0 0
Occupational Activity 0 0 0
Social Activity 0 0 0
Thesis Work 0 0 0
Field Study 0 0 0
Report Writing 0 0 0
Final Exam 1 2 2
Preparation for the Final Exam 1 35 35
Mid-Term Exam 1 2 2
Preparation for the Mid-Term Exam 1 30 30
Short Exam 0 0 0
Preparation for the Short Exam 0 0 0
TOTAL 32 0 153
Total Workload of the Course Unit 153
Workload (h) / 25.5 6
ECTS Credits allocated for the Course Unit 6,0