TÜRKÇE
ENGLISH
Information
| Code | YZ001 |
| Name | Machine Learning |
| Term | 2024-2025 Academic Year |
| Term | Fall |
| Duration (T+A) | 3-0 (T-A) (17 Week) |
| ECTS | 6 ECTS |
| National Credit | 3 National Credit |
| Teaching Language | Türkçe |
| Level | Yüksek Lisans Dersi |
| Type | Normal |
| Mode of study | Yüz Yüze Öğretim |
| Catalog Information Coordinator | |
| Course Instructor |
1 |
Course Goal / Objective
The aim of this course is to provide the mathematical and algorithmic background necessary for the computational intelligence part of Artificial Intelligence and to comprehend the use of supervised, unsupervised and reinforcement learning concepts in current artificial intelligence topologies.
Course Content
Current AI topologies of machine learning algorithms, supervised, unsupervised and reinforcement learning concepts
Course Precondition
There is no prerequisite for the course.
Resources
Tom M. Mitchell, Machine Learning , McGraw Hill, 1997, 9780070428072, 0070428077.
Notes
Ethem Alpaydın, Introduction to Machine Learning, third edition. MIT Press, 2014, 0262028182, 9780262028189.
Course Learning Outcomes
| Order | Course Learning Outcomes |
|---|---|
| LO01 | Knows error minimization and mathematical error minimization methods |
| LO02 | Solves engineering problems with Fuzzy Logic |
| LO03 | Distinguish between automated, intelligent and smart systems, realizing tutored, untutored and reinforcement learning |
| LO04 | Train artificial neural networks, use classification and regression performance scoring metrics, implement MLP, RBF, GRNN, PNN and SOM artificial neural networks in MATLAB or Phyton environment, |
| LO05 | Use support vector machine, convolutional artificial neural network, decision tree and genetic algorithm in engineering problems |
Relation with Program Learning Outcome
| Order | Type | Program Learning Outcomes | Level |
|---|---|---|---|
| PLO01 | Beceriler - Bilişsel, Uygulamalı | To be able to access information broadly and deeply by conducting scientific research in the field, to be able to evaluate, interpret and apply the information. | |
| PLO02 | Bilgi - Kuramsal, Olgusal | Has a comprehensive knowledge of current techniques and methods applied in engineering and their limitations. | |
| PLO03 | Beceriler - Bilişsel, Uygulamalı | To be able to use uncertain, limited or incomplete data to complete and apply knowledge using scientific methods; to be able to use knowledge from different disciplines together. | 4 |
| PLO04 | Bilgi - Kuramsal, Olgusal | Is aware of new and emerging practices of the profession, examines and learns them when needed. | |
| PLO05 | Beceriler - Bilişsel, Uygulamalı | Defines and formulates problems related to the field, develops methods to solve them and applies innovative methods in solutions. | 5 |
| PLO06 | Beceriler - Bilişsel, Uygulamalı | Develops new and/or original ideas and methods; designs complex systems or processes and develops innovative/alternative solutions in their designs. | 5 |
| PLO07 | Beceriler - Bilişsel, Uygulamalı | Designs and implements theoretical, experimental and modeling-based research; examines and solves complex problems encountered in this process. | |
| PLO08 | Yetkinlikler - Bağımsız Çalışabilme ve Sorumluluk Alabilme Yetkinliği | To be able to work effectively in disciplinary and multidisciplinary teams, to lead such teams and to develop solution approaches in complex situations; to be able to work independently and take responsibility. | |
| PLO09 | Bilgi - Kuramsal, Olgusal | To be able to communicate orally and in writing in a foreign language at least at the B2 level of the European Language Portfolio. | |
| PLO10 | Yetkinlikler - İletişim ve Sosyal Yetkinlik | To be able to communicate the process and results of his/her studies systematically and clearly in written or oral form in national and international environments in or outside the field. | |
| PLO11 | Yetkinlikler - İletişim ve Sosyal Yetkinlik | Knows the social, environmental, health, safety, legal, project management and business life practices of engineering applications and is aware of the constraints these impose on engineering applications. | |
| PLO12 | Bilgi - Kuramsal, Olgusal | Observes social, scientific and ethical values in the stages of data collection, interpretation and announcement and in all professional activities. |
Week Plan
| Week | Topic | Preparation | Methods |
|---|---|---|---|
| 1 | Error minimization and LMS algorithm | Preliminary research on the subject | Öğretim Yöntemleri: Anlatım |
| 2 | Tilt drop, least steps and Levenberg Marquardt algorithms | Preliminary research on the subject | Öğretim Yöntemleri: Anlatım |
| 3 | Introduction to artificial neural networks and f-scoring | Preliminary research on the subject | Öğretim Yöntemleri: Anlatım |
| 4 | Tutorial learning and Perceptron learning algorithm | Preliminary research on the subject | Öğretim Yöntemleri: Anlatım |
| 5 | MLP neural network and working with real data sets | Preliminary research on the subject | Öğretim Yöntemleri: Anlatım |
| 6 | RBF artificial neural network | Preliminary research on the subject | Öğretim Yöntemleri: Anlatım |
| 7 | GRNN and PNN artificial neural networks | Preliminary research on the subject | Öğretim Yöntemleri: Anlatım |
| 8 | Mid-Term Exam | Exam preparation | Ölçme Yöntemleri: Yazılı Sınav |
| 9 | Unsupervised learning and SOM neural network | Preliminary research on the subject | Öğretim Yöntemleri: Anlatım |
| 10 | Fuzzy Logic | Preliminary research on the subject | Öğretim Yöntemleri: Anlatım |
| 11 | Decision tree | Preliminary research on the subject | Öğretim Yöntemleri: Anlatım |
| 12 | Genetic algorithm | Preliminary research on the subject | Öğretim Yöntemleri: Anlatım |
| 13 | Lagrange interpolation | Preliminary research on the subject | Öğretim Yöntemleri: Anlatım |
| 14 | Support vector machine | Preliminary research on the subject | Öğretim Yöntemleri: Anlatım |
| 15 | Convolutional Neural Networks | Preliminary research on the subject | Öğretim Yöntemleri: Anlatım |
| 16 | Term Exams | Exam preparation | Ölçme Yöntemleri: Yazılı Sınav |
| 17 | Term Exams | Exam preparation | 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 | 1 | 15 | 15 |
| Mid-term Exams (Written, Oral, etc.) | 1 | 15 | 15 |
| Final Exam | 1 | 20 | 20 |
| Total Workload (Hour) | 162 | ||
| Total Workload / 25 (h) | 6,48 | ||
| ECTS | 6 ECTS | ||