TÜRKÇE
ENGLISH
Information
| Code | MK0034 |
| Name | Machine Learning Applications in Fluid Mechanics |
| Term | 2024-2025 Academic Year |
| Semester | . Semester |
| Duration (T+A) | 3-0 (T-A) (17 Week) |
| ECTS | 6 ECTS |
| National Credit | 3 National Credit |
| Teaching Language | İngilizce |
| Level | Yüksek Lisans Dersi |
| Type | Normal |
| Mode of study | Yüz Yüze Öğretim |
| Catalog Information Coordinator | Dr. Öğr. Üyesi Sergen TÜMSE |
Course Goal / Objective
The main objective of this course is to cover the application of different machine learning algorithms in the field of fluid mechanics, which includes applications such as prediction of aerodynamic forces and wind power.
Course Content
This course will focus on the broad heuristics that drive basic Machine Learning algorithms in the context of specific fluid mechanics applications. Matlab will be used as part of this course, but students will also be trained to implement these methods using open source packages such as TensorFlow.
Course Precondition
None
Resources
Deep Learning, Goodfellow et al, MIT Press, 20172.
Notes
Lecture Notes Pattern Recognition and Machine Learning, Christopher Bishop, Springer, 20093.
Course Learning Outcomes
| Order | Course Learning Outcomes |
|---|---|
| LO01 | Students can evaluate common machine learning methods for their effectiveness. |
| LO02 | Students can evaluate the advantages and disadvantages of the machine learning method that is planned to be used. |
| LO03 | Students can design and test basic machine learning solutions. |
| LO04 | Students identify and implement the appropriate machine learning architecture and algorithm for the envisioned. |
| LO05 | Students gain knowledge about the arrangement of machine models and optimization methods. |
Relation with Program Learning Outcome
| Order | Type | Program Learning Outcomes | Level |
|---|---|---|---|
| PLO01 | Bilgi - Kuramsal, Olgusal | Understands and applies basic sciences, mathematics and engineering sciences at a high level. | 5 |
| PLO02 | Bilgi - Kuramsal, Olgusal | He/she has extensive and in-depth knowledge, including the latest developments in his/her field. | 4 |
| PLO03 | Beceriler - Bilişsel, Uygulamalı | They reach the latest information in a field and have a high level of proficiency in the methods and skills necessary to comprehend and research them. | 4 |
| PLO04 | Beceriler - Bilişsel, Uygulamalı | They carry out a comprehensive study that brings innovation to science and technology, develops a new scientific method or technological product/process, or applies a known method to a new field. | 3 |
| PLO05 | Beceriler - Bilişsel, Uygulamalı | Independently perceives, designs, implements and concludes an original research process; manages this process. | 3 |
| PLO06 | Yetkinlikler - Bağımsız Çalışabilme ve Sorumluluk Alabilme Yetkinliği | Contributes to the science and technology literature by publishing the outputs of its academic studies in respected academic environments. | |
| PLO07 | Yetkinlikler - Bağımsız Çalışabilme ve Sorumluluk Alabilme Yetkinliği | Evaluates scientific, technological, social and cultural developments and conveys them to the society with the awareness of scientific impartiality and ethical responsibility. | |
| PLO08 | Yetkinlikler - İletişim ve Sosyal Yetkinlik | Performs critical analysis, synthesis and evaluation of ideas and developments in the field of expertise. | |
| PLO09 | Yetkinlikler - İletişim ve Sosyal Yetkinlik | Communicates effectively, both verbally and in writing, with those working in the field of specialization and the wider scientific and social community, communicating and discussing at an advanced level of written, oral and visual communication using a foreign language at least at the C1 General Level of the European Language Portfolio. | |
| PLO10 | Yetkinlikler - Bağımsız Çalışabilme ve Sorumluluk Alabilme Yetkinliği | Carring out literature survey | 5 |
Week Plan
| Week | Topic | Preparation | Methods |
|---|---|---|---|
| 1 | Mathematical Basics 1 – Introduction to Machine Learning, Linear Algebra | Lecture notes | Öğretim Yöntemleri: Anlatım, Soru-Cevap |
| 2 | Mathematical Basics 2 - Probability | Lecture notes | Öğretim Yöntemleri: Anlatım |
| 3 | Computational Basics – Numerical computation and optimization, Introduction to Machine learning packages | Lecture notes | Öğretim Yöntemleri: Anlatım, Tartışma |
| 4 | Linear and Logistic Regression – Bias/Variance Tradeoff, Regularization, Variants of Gradient Descent, MLE, MAP, Applications | Lecture notes | Öğretim Yöntemleri: Anlatım, Gösteri |
| 5 | Neural Networks – Multilayer Perceptron, Backpropagation, Applications | Lecture notes | Öğretim Yöntemleri: Anlatım, Gösteri, Gösterip Yaptırma |
| 6 | Convolutional Neural Networks 1 – CNN Operations, CNN architectures | Lecture notes | Öğretim Yöntemleri: Anlatım |
| 7 | Convolutional Neural Networks 2 – Training, Transfer Learning, Applications | Lecture notes | Öğretim Yöntemleri: Anlatım, Soru-Cevap |
| 8 | Mid-Term Exam | Lecture notes | Ölçme Yöntemleri: Yazılı Sınav |
| 9 | Application of Convolutional Neural Networks in the estimation of wind power | Lecture notes | Öğretim Yöntemleri: Anlatım, Soru-Cevap |
| 10 | Application of Convolutional Neural Networks in the estimation of wing aerodynamic forces | Lecture notes | Öğretim Yöntemleri: Anlatım, Soru-Cevap |
| 11 | Recurrent Neural Networks RNN, LSTM, GRU, Applications | Lecture notes | Öğretim Yöntemleri: Anlatım, Soru-Cevap |
| 12 | Classical Techniques 1 – Bayesian Regression, Applications | Lecture notes | Öğretim Yöntemleri: Anlatım, Soru-Cevap |
| 13 | Classical Techniques 2 – k-Means, kNN, GMM, Expectation Maximization, Applications | Lecture notes | Öğretim Yöntemleri: Soru-Cevap, Anlatım |
| 14 | Advanced Techniques 1 – Structured Probabilistic Models, Monte Carlo Methods | Lecture notes | Öğretim Yöntemleri: Soru-Cevap, Anlatım |
| 15 | Advanced Techniques 2 – Autoencoders, Generative Adversarial Network | Lecture notes | Öğretim Yöntemleri: Anlatım |
| 16 | Term Exams | Lecture notes | Ölçme Yöntemleri: Yazılı Sınav |
| 17 | Term Exams | Lecture notes | Ölçme Yöntemleri: Yazılı Sınav |
Student Workload - ECTS
| Works | Number | Time (Hour) | Workload (Hour) |
|---|---|---|---|
| Course Related Works | |||
| Class Time (Exam weeks are excluded) | 14 | 3 | 42 |
| Out of Class Study (Preliminary Work, Practice) | 14 | 5 | 70 |
| Assesment Related Works | |||
| Homeworks, Projects, Others | 0 | 0 | 0 |
| Mid-term Exams (Written, Oral, etc.) | 1 | 15 | 15 |
| Final Exam | 1 | 30 | 30 |
| Total Workload (Hour) | 157 | ||
| Total Workload / 25 (h) | 6,28 | ||
| ECTS | 6 ECTS | ||