ECTSNeural Networks and Applications

Neural Networks and Applications (EE423) Ders Detayları

Course Name Corse Code Dönemi Lecture Hours Uygulama Saati Lab Hours Credit ECTS
Neural Networks and Applications EE423 Elective Courses 3 0 0 3 5
Pre-requisite Course(s)
N/A
Course Language İngilizce
Course Type Technical Elective Courses
Course Level Lisans
Mode of Delivery Face To Face
Learning and Teaching Strategies Lecture, Demonstration, Discussion, Question and Answer, Drill and Practice, Team/Group, Brain Storming.
Course Coordinator
Course Lecturer(s)
  • Asst. Prof. Dr. Hakan Tora
Course Assistants
Course Objectives •Introduce the main fundamental principles and techniques of neural network systems. •Investigate the principal neural network models and applications.
Course Learning Outcomes The students who succeeded in this course;
  • Ability to describe the relation between real brains and simple artificial neural network models
  • Ability to explain and contrast the most common architectures and learning algorithms for Multi-Layer Perceptrons, Radial-Basis Function Networks, Committee Machines, and Kohonen Self-Organizing Maps
  • Ability to identify different neural network architectures, their limitations and appropriate learning rules for each of the architectures
  • Ability to verify the classic linear separability problem that exists for single layer networks, demonstrate and explain how adding a hidden layer solves the problem
  • Ability to discuss the main factors involved in achieving good learning and generalization performance in neural network systems
  • Ability to design and implement neural network systems to solve real-world problems (classification, pattern recognition)
Course Content An introduction to basic neurobiology, the main neural network architectures and learning algorithms, and a number of neural network applications, McCulloch Pitts Neurons, Single Layer Perceptrons, Multi-Layer Perceptrons, Radial Basis Function Networks, Committee Machines, Kohonen Self-Organising Maps, and Learning Vector Quantization

Weekly Subjects and Releated Preparation Studies

Week Subjects Preparation
1 Introduction to Neural Networks and their History. Biological Neurons and Neural Networks. Artificial Neurons Glance this week’s topics from the lecture
2 Networks of Artificial Neurons. Single Layer Perceptrons. Learning and Generalization in Single Layer Perceptrons Glance this week’s topics from the lecture
3 Hebbian Learning. Gradient Descent Learning Glance this week’s topics from the lecture
4 The Generalized Delta Rule. Practical Considerations Glance this week’s topics from the lecture
5 Learning in Multi-Layer Perceptrons. Back-Propagation Algorithms Glance this week’s topics from the lecture
6 Learning with Momentum. Conjugate Gradient Learning Review last week and glance this week’s topics from the lecture
7 Bias and Variance. Under-Fitting and Over-Fitting. Improving Generalization Review last week and glance this week’s topics from the lecture
8 Applications of Multi-Layer Perceptrons Glance this week’s topics from the lecture
9 Radial Basis Function Networks: Introduction, Algorithms, and Applications Glance this week’s topics from the lecture
10 Associative learning Glance this week’s topics from the lecture
11 Competitive networks, Counterpropagation networks, Grossberg networks Glance this week’s topics from the lecture
12 Adaptive resonance theory, stability Glance this week’s topics from the lecture
13 Hopfield networks, bidirectional associative memories Glance this week’s topics from the lecture
14 Self Organizing Maps: Fundamentals, Algorithms, and Applications Glance this week’s topics from the lecture
15 Final examination period Review topics
16 Fimal examination period Review topics

Sources

Course Book 1. Neural Networks: A Comprehensive Foundation, Simon Haykin, Pearson Education Inc. Leicestershire U.K 1999
Other Sources 2. Neural Networks for Pattern Recognition, C. Bishop, Oxford University Press, 1995
3. Principles of Neurocomputing for Science and Engineering, F.M.Ham and I.Kostanic, McGraw Hill, 2001

Evaluation System

Requirements Number Percentage of Grade
Attendance/Participation - -
Laboratory - -
Application - -
Field Work - -
Special Course Internship - -
Quizzes/Studio Critics - -
Homework Assignments 15 20
Presentation - -
Project 1 20
Report - -
Seminar - -
Midterms Exams/Midterms Jury 2 30
Final Exam/Final Jury 1 30
Toplam 19 100
Percentage of Semester Work 70
Percentage of Final Work 30
Total 100

Course Category

Core Courses
Major Area Courses X
Supportive Courses
Media and Managment Skills Courses
Transferable Skill Courses

The Relation Between Course Learning Competencies and Program Qualifications

# Program Qualifications / Competencies Level of Contribution
1 2 3 4 5
1 Accumulated knowledge on mathematics, science and mechatronics engineering; an ability to apply the theoretical and applied knowledge of mathematics, science and mechatronics engineering to model and analyze mechatronics engineering problems. X
2 An ability to differentiate, identify, formulate, and solve complex engineering problems; an ability to select and implement proper analysis, modeling and implementation techniques for the identified engineering problems. X
3 An ability to design a complex system, product, component or process to meet the requirements under realistic constraints and conditions; an ability to apply contemporary design methodologies; an ability to implement effective engineering creativity techniques in mechatronics engineering. (Realistic constraints and conditions may include economics, environment, sustainability, producibility, ethics, human health, social and political problems.) X
4 An ability to develop, select and use modern techniques, skills and tools for application of mechatronics engineering and robot technologies; an ability to use information and communications technologies effectively. X
5 An ability to design experiments, perform experiments, collect and analyze data and assess the results for investigated problems on mechatronics engineering and robot technologies. X
6 An ability to work effectively on single disciplinary and multi-disciplinary teams; an ability for individual work; ability to communicate and collaborate/cooperate effectively with other disciplines and scientific/engineering domains or working areas, ability to work with other disciplines. X
7 An ability to express creative and original concepts and ideas effectively in Turkish and English language, oral and written, and technical drawings.
8 An ability to reach information on different subjects required by the wide spectrum of applications of mechatronics engineering, criticize, assess and improve the knowledge-base; consciousness on the necessity of improvement and sustainability as a result of life-long learning; monitoring the developments on science and technology; awareness on entrepreneurship, innovative and sustainable development and ability for continuous renovation.
9 Consciousness on professional and ethical responsibility, competency on improving professional consciousness and contributing to the improvement of profession itself.
10 A knowledge on the applications at business life such as project management, risk management and change management and competency on planning, managing and leadership activities on the development of capabilities of workers who are under his/her responsibility working around a project.
11 Knowledge about the global, societal and individual effects of mechatronics engineering applications on the human health, environment and security and cultural values and problems of the era; consciousness on these issues; awareness of legal results of engineering solutions.
12 Competency on defining, analyzing and surveying databases and other sources, proposing solutions based on research work and scientific results and communicate and publish numerical and conceptual solutions.
13 Consciousness on the environment and social responsibility, competencies on observation, improvement and modify and implementation of projects for the society and social relations and be an individual within the society in such a way that planing, improving or changing the norms with a criticism.

ECTS/Workload Table

Activities Number Duration (Hours) Total Workload
Course Hours (Including Exam Week: 16 x Total Hours) 16 3 48
Laboratory
Application
Special Course Internship
Field Work
Study Hours Out of Class 16 2 32
Presentation/Seminar Prepration
Project 4 5 20
Report
Homework Assignments 8 2 16
Quizzes/Studio Critics
Prepration of Midterm Exams/Midterm Jury 2 3 6
Prepration of Final Exams/Final Jury 1 3 3
Total Workload 125