TÜRKÇE
ENGLISH
Information
| Unit | |
| Code | SD0762 |
| Name | Fundamentals of Machine Learning and Deep Learning |
| Term | 2025-2026 Academic Year |
| Term | Fall and Spring |
| Duration (T+A) | 2-0 (T-A) (17 Week) |
| ECTS | 3 ECTS |
| National Credit | 2 National Credit |
| Teaching Language | Türkçe |
| Level | Üniversite Dersi |
| Label | UCC University Common Course |
| Mode of study | Yüz Yüze Öğretim |
| Catalog Information Coordinator | Öğr. Gör. Eşref ERDOĞAN |
| Course Instructor |
The current term course schedule has not been prepared yet.
|
Course Goal / Objective
This course aims to teach the basic principles of machine learning and deep learning. It provides students with basic knowledge about working with data, understanding model logic, and current application areas.
Course Content
This course aims to introduce the concepts of machine learning and deep learning at a basic level. It explains what supervised, unsupervised, and reinforcement learning are and focuses on the roles of these techniques in the world of machine learning. The definition of deep learning and how it differs from machine learning is explained in an understandable language within the scope of the basic structure and functioning of artificial neural networks. These concepts are concretized with application examples such as image recognition, text processing or recommendation systems used in daily life.
Course Precondition
Resources
•Géron, A. Applied Machine Learning with Scikit-Learn, Keras and TensorFlow (Fundamentals)
Notes
Dataset resources available on the web
Course Learning Outcomes
| Order | Course Learning Outcomes |
|---|---|
| LO01 | Defines the concept and types of machine learning. |
| LO02 | Explain the differences between supervised, unsupervised and reinforcement learning. |
| LO03 | Explains the concept of deep learning and its difference from machine learning. |
| LO04 | Understands the basic logic of artificial neural networks. |
| LO05 | It performs simple classification and prediction applications with ready-made tools. |
| LO06 | Recognizes model evaluation criteria. |
Week Plan
| Week | Topic | Preparation | Methods |
|---|---|---|---|
| 1 | Introduction to Machine Learning | No preparation required | Öğretim Yöntemleri: Anlatım, Gösteri, Tartışma |
| 2 | Types of Machine Learning | No preparation required | Öğretim Yöntemleri: Anlatım, Tartışma, Gösteri, Örnek Olay |
| 3 | Data Concept | No preparation required | Öğretim Yöntemleri: Anlatım, Gösteri, Tartışma |
| 4 | Data Preprocessing | No preparation required | Öğretim Yöntemleri: Anlatım, Tartışma, Gösteri, Örnek Olay |
| 5 | Supervised Learning Methods | No preparation required | Öğretim Yöntemleri: Anlatım, Tartışma, Gösteri, Beyin Fırtınası |
| 6 | Unsupervised Learning | No preparation required | Öğretim Yöntemleri: Anlatım, Tartışma, Gösteri, Örnek Olay |
| 7 | Introduction to Deep Learning | No preparation required | Öğretim Yöntemleri: Anlatım, Örnek Olay, Gösteri |
| 8 | Mid-Term Exam | Preliminary Preparation Required | Ölçme Yöntemleri: Yazılı Sınav |
| 9 | Fundamentals of Artificial Neural Networks | No preparation required | Öğretim Yöntemleri: Anlatım, Tartışma, Gösteri |
| 10 | Convolutional Neural Networks (CNN) | No preparation required | Öğretim Yöntemleri: Soru-Cevap, Gösteri, Örnek Olay |
| 11 | Recurrent Neural Networks (RNN, LSTM) | No preparation required | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma, Gösteri, Örnek Olay |
| 12 | Transfer Learning | No preparation required | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Gösteri, Örnek Olay |
| 13 | Model Performance Measurement | No preparation required | Öğretim Yöntemleri: Anlatım, Gösteri, Beyin Fırtınası, Örnek Olay |
| 14 | Application Examples | No preparation required | Öğretim Yöntemleri: Soru-Cevap, Gösteri, Örnek Olay |
| 15 | General Evaluation | No preparation required | Öğretim Yöntemleri: Anlatım, Tartışma, Beyin Fırtınası |
| 16 | Term Exams | Preliminary Preparation Required | Ölçme Yöntemleri: Yazılı Sınav |
| 17 | Term Exams | Preliminary Preparation Required | Ölçme Yöntemleri: Yazılı Sınav |
Student Workload - ECTS
| Works | Number | Time (Hour) | Workload (Hour) |
|---|---|---|---|
| Course Related Works | |||
| Class Time (Exam weeks are excluded) | 14 | 2 | 28 |
| Out of Class Study (Preliminary Work, Practice) | 14 | 2 | 28 |
| Assesment Related Works | |||
| Homeworks, Projects, Others | 1 | 10 | 10 |
| Mid-term Exams (Written, Oral, etc.) | 1 | 1 | 1 |
| Final Exam | 1 | 1 | 1 |
| Total Workload (Hour) | 68 | ||
| Total Workload / 25 (h) | 2,72 | ||
| ECTS | 3 ECTS | ||