2024 Faculty Courses School of Engineering Department of Systems and Control Engineering Graduate major in Systems and Control Engineering
Machine Learning Framework
- Academic unit or major
- Graduate major in Systems and Control Engineering
- Instructor(s)
- Yusuke Miyazaki / Koji Kitamura
- Class Format
- Lecture (Face-to-face)
- Media-enhanced courses
- -
- Day of week/Period
(Classrooms) - 5-6 Thu
- Class
- -
- Course Code
- SCE.I406
- Number of credits
- 100
- Course offered
- 2024
- Offered quarter
- 2Q
- Syllabus updated
- Mar 14, 2025
- Language
- Japanese
Syllabus
Course overview and goals
This course gives lectures and practical exercises on machine learning algorithms and cultivates the ability to implement the algorithm with actual data by using Python code. Specifically, this course introduces the basics of machine learning, unsupervised learning, and supervised learning. In addition, the basics of deep learning algorithms are also covered.
Course description and aims
Students will acquire the following skills by taking this course.
1) Be able to understand the basic concepts of machine learning algorithms and Python programming． Also, be able to understand the concepts and applications of other methods not covered in the lectures.
2) Be able to select and implement machine learning methods for your own purposes
Keywords
Machine learning, programming, Python, algorithm
Competencies
- Specialist skills
- Intercultural skills
- Communication skills
- Critical thinking skills
- Practical and/or problem-solving skills
Class flow
Brief lectures are given in the first half of each class. Then, students will tackle practical exercises on the given contents.
Course schedule/Objectives
| Course schedule | Objectives | |
|---|---|---|
| Class 1 | Python installation, basics of Python code | Preparing a Python development environment for basic programming. |
| Class 2 | Basics of machine learning, unsupervised learing and thier practical exercises | Understanding the basics of machine learning and the procedures for unsupervised learning. |
| Class 3 | Practical Exercise | Practical exercise on unsupervised learning based on actual data. |
| Class 4 | Basics of supervised learning and its exercise | Understanding the basics of supervised learning. |
| Class 5 | Practical Exercise | Practical exercise on supervised learning based on actual data. |
| Class 6 | Basics of deep learning and its exercise | Understanding the basics of deep learning. |
| Class 7 | Practical exercise | Practical exercise on deep learning based on actual data. |
Study advice (preparation and review)
To enhance effective learning, students are encouraged to spend approximately 100 minutes preparing for class and another 100 minutes reviewing class content afterwards (including assignments) for each class.
They should do so by referring to textbooks and other course material.
Textbook(s)
None
Reference books, course materials, etc.
Course materials will be distributed at the class
Evaluation methods and criteria
Assessed by the three exercises.
Related courses
- SCE.Z401 ： Cyber-Physical Innovation
Prerequisites
None
Other
Since this course has exercise, the number of students might be restricted in some case.