Syllabus
Course: Special Topics in Artificial Intelligence Instructor: To be announced Format: Lectures · hands-on practice · discussion · project-based learning
Course Overview
This course introduces selected topics in modern and applied artificial intelligence. It covers advanced predictive modeling, sequential data analysis, anomaly detection, explainable AI, generative approaches, optimization, and data-efficient learning. The course integrates conceptual understanding, practical applications, case analysis, and project-based activities.
Artificial intelligence is increasingly used to support prediction, automation, interpretation, and decision-making across engineering and industrial domains. This course helps students understand advanced AI concepts beyond introductory machine learning and develop the ability to evaluate, apply, and communicate AI methods in real-world problem-solving contexts.
Course Objectives
The course aims to develop students’ ability to:
- understand advanced AI methodologies,
- formulate practical problems as AI tasks,
- select and evaluate appropriate models,
- interpret analytical results,
- assess methodological limitations.
Students will also strengthen their ability to analyze AI applications and develop an integrated AI-based project.
Prerequisites
Basic knowledge of programming, statistics, data analysis, or machine learning is recommended. Familiarity with Python and fundamental data-processing concepts will be helpful for practical activities.
Teaching Methods
The course combines four teaching methods:
| Method | Description |
|---|---|
| Lecture | Conceptual foundations of each topic |
| Lab / hands-on practice | Practical application sessions |
| Discussion (Havruta) | Paired/technical discussion of methods and case studies |
| Project-Based Learning (PBL) | Integrated semester project developed across the course |
The course covers applied AI research and problem formulation, deep learning for structured data, time-series modeling, anomaly detection, explainable and trustworthy AI, generative modeling, inverse design, AI-based optimization, and active learning. Each major topic is connected to practical applications, case studies, technical discussion, and semester project development.
Assessment
Evaluation focuses on students’ understanding of AI concepts, ability to analyze practical applications, interpretation of model results, critical assessment of methodologies, and development of an integrated AI project. Students will be assessed through participation, assignments, examinations, project planning, practical analysis, and final project outcomes.
Grading Breakdown
■ Attendance · ■ Assignments · ■ Midterm Examination · ■ Final Examination · ■ Other
| Component | Weight |
|---|---|
| Attendance | 10% |
| Assignments | 20% |
| Midterm Examination | 20% |
| Final Examination | 20% |
| Other | 30% |
| Total | 100% |
Weekly Topics
| Week | Topic |
|---|---|
| 1 | Course Introduction and Overview of Applied Artificial Intelligence |
| 2 | Machine Learning Strategy and Best Practices |
| 3 | Deep Learning for Structured and Engineering Data |
| 4 | Practical Applications of Deep Learning |
| 5 | Time-Series Forecasting and Anomaly Detection |
| 6 | Practical Applications of Time-Series and Anomaly Detection |
| 7 | AI Project Proposal and Planning |
| 8 | Midterm Examination |
| 9 | Explainable and Trustworthy Artificial Intelligence |
| 10 | Practical Applications of Explainable AI |
| 11 | Generative Modeling, Inverse Design, and AI-Based Optimization |
| 12 | Active Learning and Data-Efficient Artificial Intelligence |
| 13 | Practical Applications of Generative Modeling and Data-Efficient AI |
| 14 | Final Project Presentation and Demonstration |
| 15 | Final Examination |
See the Schedule page for the current status of each week’s materials.