BİLGİ PAKETİ / DERS KATALOĞU
| NAVAL ARCHITECTURE AND MARINE ENGINEERING HIGH PERFORMANCE MARINE PLATFORMS | |||||
|---|---|---|---|---|---|
| Qualification Awarded | Length of Program | Toplam Kredi (AKTS) | Mode of Study | Level of Qualification & Field of Study | |
| Master's ( Second Cycle) Degree | 2 | 120 | FULL TIME |
TQF, TQF-HE, EQF-LLL, ISCED (2011):Level 7 QF-EHEA:Second Cycle TQF-HE, ISCED (1997-2013): |
|
General Course Description Information
| Course Code: | EEE555 | ||||||||
| Course Name: | ARTIFICIAL NEURAL NETWORKS AND ENGINEERING APPLICATIONS | ||||||||
| Course Semester: |
Spring Fall |
||||||||
| Course Credits: |
|
||||||||
| Language of instruction: | English | ||||||||
| Condition of Course: | |||||||||
| Does the Course Work Experience Require?: | No | ||||||||
| Course Type : | Bölüm/Program Seçmeli | ||||||||
| Course Level: |
|
||||||||
| Mode of Delivery: | Face to face | ||||||||
| Name of Coordinator: | Dr. Öğr. Üyesi Erdem BİLGİLİ | ||||||||
| Course Lecturer(s): | Asst.Prof. Dr. Erdem Bilgili | ||||||||
| Course Assistants: |
Objective and Contents of the Course
| Course Objectives: | The course is basically an introduction to the artificial intelligence. ANN and Genetic algorithms is introduced to the students. Fundamental concepts of the fuzzy logics, deep learning neural networks and their applications are studied.. 1. Students learn the fundamentals of artificial neural networks, such as multilayer Feedforward ANN, Cellular Neural Network, Hopfield Nets. 2. Students learn how to apply neural networks for forecasting and optimisation applications 3. Students study, genetic algorithms and its applications. 4. Students are introduced fundamental concepts of the fuzzy logic such as fuzzy sets, fuzzification, defuzzification. 5. Students will learn how to combine ANN, Fuzzy Logic Systems, and Genetic Algorithm for a specific purposes. |
| Course Content: | Introduction to Computers Artificial Intelligence Human Brain , Computers, Artificial Neural Network Multilayer Neural Networks Backpropagation Self Organising Maps Fuzzy Logics Genetic Algorithms, Genetic Operators MIDTERM Optimisation with GA Hopfield Networks Deep Learning Tensor Flows and Deep Beliefs Review |
Learning Outcomes
|
The students who have succeeded in this course;
1) I. Understand the importance of artificial intelligent techniques. 2) II. Be able to analyze and design artificial neural network system. 3) III. Understand and be able to determine the stability of a dynamic neural network. 4) IV. Use and understand fuzzy logic systems 5) V. Know how a GA could be applied for any optimization tasks 6) VI. Know the basic definition of the pattern recognition tasks and ANN applications 7) VII. Use ANN for analysis and design of control systems 8) VIII. Know the design ANN for forecasting applications |
Ders Akış Planı
| Week | Subject | Related Preparation |
| 1) | Introduction to Computers | |
| 2) | Artificial Intelligence | |
| 3) | Human Brain , Computers, Artificial Neural Network | |
| 4) | Multilayer Neural Networks | |
| 5) | Backpropagation | |
| 6) | Self Organizing Maps | |
| 7) | Fuzzy Logics | |
| 8) | Genetic Algorithms, Genetic Operators | |
| 9) | MIDTERM | |
| 10) | Optimization with GA | |
| 11) | Hopfield Networks | |
| 12) | Deep Learning | |
| 13) | Tensor Flows and Deep Beliefs | |
| 14) | Review |
Sources
| Course Notes / Textbooks: | • Principles of Artificial Neural Networks, Daniel Graupe • Dorf and Bishop, Modern Control Systems, 12 /E, Prentice Hall, 2011. ISBN-10: 0136024580, ISBN-13: 9780136024583. |
| References: | • Principles of Artificial Neural Networks, Daniel Graupe • Dorf and Bishop, Modern Control Systems, 12 /E, Prentice Hall, 2011. ISBN-10: 0136024580, ISBN-13: 9780136024583. |
Contribution of The Course Unit To The Programme Learning Outcomes
| Course Learning Outcomes | 1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
|---|---|---|---|---|---|---|---|---|
| Program Outcomes | ||||||||
| 1) Repeats the current techniques and methods applied in the field of technology and their limitations, effects and results | ||||||||
| 2) Completes and implements knowledge with scientific methods using limited or incomplete data; integrates knowledge of different disciplines | ||||||||
| 3) Models and applies experimental studies and solves complex situations in the process | ||||||||
| 4) Leads in multidisciplinary teams in the field of technology | ||||||||
| 5) Uses the methods and software used in the field of technology and communication technologies at advanced level | ||||||||
| 6) Observes social, scientific and ethical values in the collection, interpretation, application and announcement phases of data in all professional activities | ||||||||
| 7) Applies research in the field of Naval Architecture to expand and deepen knowledge, evaluates and applies knowledge for problem solving in a strategic and genuine fashion | ||||||||
| 8) Transfers the processes and results of the work in a systematic way in written, verbal and visual form in the national and international area | ||||||||
Course - Learning Outcomes
| No Effect | 1 Lowest | 2 Average | 3 Highest |
| Program Outcomes | Level of Contribution | |
| 1) | Repeats the current techniques and methods applied in the field of technology and their limitations, effects and results | |
| 2) | Completes and implements knowledge with scientific methods using limited or incomplete data; integrates knowledge of different disciplines | |
| 3) | Models and applies experimental studies and solves complex situations in the process | |
| 4) | Leads in multidisciplinary teams in the field of technology | |
| 5) | Uses the methods and software used in the field of technology and communication technologies at advanced level | |
| 6) | Observes social, scientific and ethical values in the collection, interpretation, application and announcement phases of data in all professional activities | |
| 7) | Applies research in the field of Naval Architecture to expand and deepen knowledge, evaluates and applies knowledge for problem solving in a strategic and genuine fashion | |
| 8) | Transfers the processes and results of the work in a systematic way in written, verbal and visual form in the national and international area |
Learning Activities and Teaching Methods
Assessment & Evaluation Methods of the Course Unit
Assessment & Grading
| Semester Requirements | Number of Activities | Level of Contribution |
| Homework Assignments | 1 | % 10 |
| Presentation | 1 | % 10 |
| Midterms | 1 | % 40 |
| Semester Final Exam | 1 | % 40 |
| Total | % 100 | |
| PERCENTAGE OF SEMESTER WORK | % 60 | |
| PERCENTAGE OF FINAL WORK | % 40 | |
| Total | % 100 | |
Workload & ECTS Credits of The Course Unit
| Aktiviteler | Number of Activities | Duration (Hours) | Workload |
| Course | 13 | 3 | 39 |
| Application | 12 | 1 | 12 |
| Study Hours Out of Class | 12 | 1 | 12 |
| Presentations / Seminar | 1 | 5 | 5 |
| Project | 1 | 5 | 5 |
| Homework Assignments | 1 | 6 | 6 |
| Midterms | 1 | 15 | 15 |
| Semester Final Exam | 1 | 10 | 10 |
| Total Workload | 104 | ||