Nevşehir Hacı Bektaş Veli University Course Catalogue
|
|||||
| Year/Semester of Study | 1 / Spring Semester | ||||
| Level of Course | 2nd Cycle Degree Programme | ||||
| Type of Course | Optional | ||||
| Department | ELECTRICAL AND ELECTRONICS ENGINEERING (MASTER) | ||||
| Pre-requisities and Co-requisites | None | ||||
| Mode of Delivery | Face to Face | ||||
| Teaching Period | 14 Weeks | ||||
| Name of Lecturer | AYŞE KOCALMIŞ BİLHAN (akbilhan@nevsehir.edu.tr) | ||||
| Name of Lecturer(s) | |||||
| Language of Instruction | Turkish | ||||
| Work Placement(s) | None | ||||
| Objectives of the Course | |||||
| The basic concepts of Machine Learning will be given and various applications will be made on the computer by using Genetic Algorithms. | |||||
| Learning Outcomes | PO | MME | |
| The students who succeeded in this course: | |||
| LO-1 | Will have basic knowledge of machine learning and genetic algorithms. |
PO-1 Sufficient knowledge in mathematics, science and engineering related to their branches; the ability to apply theoretical and practical knowledge in these areas to model and solve engineering problems. PO-2 The ability to identify, formulate, and solve complex engineering problems; selecting and applying appropriate analysis and modeling methods for this purpose. PO-5 Ability to design experiments, conduct experiments, collect data, analyze and interpret results for examination of engineering problems. PO-6 The ability to work effectively in disciplinary and multidisciplinary teams; individual work skill. PO-9 Professional and ethical responsibility. |
Examination |
| LO-2 | Will learn the basic methods of machine learning and genetic algorithms. |
PO-1 Sufficient knowledge in mathematics, science and engineering related to their branches; the ability to apply theoretical and practical knowledge in these areas to model and solve engineering problems. PO-2 The ability to identify, formulate, and solve complex engineering problems; selecting and applying appropriate analysis and modeling methods for this purpose. PO-5 Ability to design experiments, conduct experiments, collect data, analyze and interpret results for examination of engineering problems. PO-6 The ability to work effectively in disciplinary and multidisciplinary teams; individual work skill. PO-8 Awareness of the need for lifelong learning; access to knowledge, ability to follow developments in science and technology, and constant self-renewal. |
Examination |
| LO-3 | Simulates the basic methods of machine learning and genetic algorithms with a computer. |
PO-1 Sufficient knowledge in mathematics, science and engineering related to their branches; the ability to apply theoretical and practical knowledge in these areas to model and solve engineering problems. PO-2 The ability to identify, formulate, and solve complex engineering problems; selecting and applying appropriate analysis and modeling methods for this purpose. PO-5 Ability to design experiments, conduct experiments, collect data, analyze and interpret results for examination of engineering problems. PO-7 Effective communication skills in Turkish oral and written communication; at least one foreign language knowledge. |
Examination |
| PO: Programme Outcomes MME:Method of measurement & Evaluation |
|||
| Course Contents | ||
| Basic concepts of machine learning. Feature extraction methods. Classifiers. Artificial neural networks. Evolution algorithms. Genetic algorithms. Genetic learning. Training of artificial neural networks with genetic algorithms. | ||
| Weekly Course Content | ||
| Week | Subject | Learning Activities and Teaching Methods |
| 1 | Temel Kavramlar; Bilginin temsil edilme şekilleri, bilgi temsilleri arasındaki dönüşümler. | Lecture, Question and Answer, Discussion |
| 2 | Feature extraction methods. | Lecture, Question and Answer, Discussion |
| 3 | Feature extraction methods. | Lecture, Question and Answer, Discussion |
| 4 | Bayesian Classifier, K-means, K-nearest neighbor classifier. | Lecture, Question and Answer, Discussion |
| 5 | Introduction to Artificial Neural Networks. | Lecture, Question and Answer, Discussion |
| 6 | Multilayer Network, Kohonen network. | Lecture, Question and Answer, Discussion |
| 7 | LVQ, GAL, RCE, Hopfield networks. | Lecture, Question and Answer, Discussion |
| 8 | mid-term exam | |
| 9 | Evolution algorithms. | Lecture, Question and Answer, Discussion |
| 10 | Introduction to genetic algorithms, Duplication, crossover and mutation | Lecture, Question and Answer, Discussion |
| 11 | Genetic pool, compatibility function, coding, scaling. | Lecture, Question and Answer, Discussion |
| 12 | Schema theorem, structural-block hypothesis. | Lecture, Question and Answer, Discussion |
| 13 | Genetic learning. | Lecture, Question and Answer, Discussion |
| 14 | Training of artificial neural networks with genetic algorithms. | Lecture, Question and Answer, Discussion |
| 15 | Training of artificial neural networks with genetic algorithms. | Lecture, Question and Answer, Discussion |
| 16 | final exam | |
| Recommend Course Book / Supplementary Book/Reading | ||
| Required Course instruments and materials | ||
| laptop, book | ||
| Assessment Methods | |||
| Type of Assessment | Week | Hours | Weight(%) |
| mid-term exam | 8 | 1 | 40 |
| Other assessment methods | |||
| 1.Oral Examination | |||
| 2.Quiz | |||
| 3.Laboratory exam | |||
| 4.Presentation | |||
| 5.Report | |||
| 6.Workshop | |||
| 7.Performance Project | |||
| 8.Term Paper | |||
| 9.Project | |||
| final exam | 16 | 1 | 60 |
| Student Work Load | |||
| Type of Work | Weekly Hours | Number of Weeks | Work Load |
| Weekly Course Hours (Theoretical+Practice) | 3 | 14 | 42 |
| Outside Class | |||
| a) Reading | 3 | 10 | 30 |
| b) Search in internet/Library | 3 | 10 | 30 |
| c) Performance Project | 0 | ||
| d) Prepare a workshop/Presentation/Report | 0 | ||
| e) Term paper/Project | 0 | ||
| Oral Examination | 0 | ||
| Quiz | 0 | ||
| Laboratory exam | 0 | ||
| Own study for mid-term exam | 4 | 10 | 40 |
| mid-term exam | 1 | 1 | 1 |
| Own study for final exam | 4 | 10 | 40 |
| final exam | 1 | 1 | 1 |
| 0 | |||
| 0 | |||
| Total work load; | 184 | ||