#Syllabus for a two-week Data Science in Astronomy course
Assumptions
- 6 hours/day, 5 days/week.
- Previous programming experience
- Basic Linear Algebra knowledge
Day 1. Basics of Python
Day 2. Philosophy of Machine Learning. Astronomical Datasets and Questions.
Day 3. Unsupervised Learning. Density estimation.
Day 4. Unsupervised Learning. Clustering.
Day 5. Unsupervised Learning. Dimensionality Reduction. PCA.
Day 6. Supervised Learning. Regression. Linear Regression. LASSO.
Day 7. Supervised Learning. Regression. Bayesian methods.
Day 8. Supervised Learning. Classification. Support Vector Machines.
Day 9. Supervised Learning. Classification. Trees and random forests.
Day 10. Project.
Notes:
- Based on the AstroML: Machine Learning and Data Mining for Astronomy book/library.
- The closest Coursera course from the JHU Data Science Specialization is Course 8: Practical Machine Learning.