Benjamin L'Huillier
Assistant Professor, Sejong University
Fall 2025
This course offers an in-depth introduction to modern statistical and machine learning methods applied to data analysis in physics and astronomy. Emphasis is placed on both theoretical foundations and practical implementation. Students will gain hands-on experience working with real or simulated astronomical data using Python-based tools.
Topics include estimation theory, hypothesis testing, goodness-of-fit, cross-validation, information criteria, Bayesian inference, and probabilistic programming.
Each class is structured into:
- 🧠 Theory – lectures on core concepts in statistics and data science
- 💻 Practice – hands-on coding sessions using Python (Jupyter notebooks or other preferred tools)
- 🏠 Homework Assignments: Regular assignments with hands-on coding problems
- 🗣️ Homework Presentations: One group presents each assignment in class
- 📊 Final Project: Student-defined topic (with instructor approval) involving astronomical data analysis
- 📄 Final Report (30%)
- 🧑🏫 Final Presentation (15%)
- 📝 Homework (30%)
- 🎙️ Homework Presentation (15%)
- 📅 Attendance and Participation (10%)
Students are encouraged to define their own final project topics (observational or simulated data). The project should demonstrate both a sound methodological approach and clarity in scientific communication.
See the Project Guidelines for more details.
Explore the content through interactive Jupyter notebooks:
- D. Green's Physics Lecture
- K. Tadai’s Astroinformatics
- D. Gerosa’s Scientific Computing
- Khuyen Tran’s Python Tips
This material is distributed under the Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0).
You are free to use, adapt, and share the content for non-commercial purposes with proper attribution.
Spotted a typo? Have suggestions for improvement?
Feel free to reach out or open an issue. Contributions are welcome!