PřF:F5611 Machine learning in Python - Course Information
F5611 Introduction to Machine learning for astronomers in Python
Faculty of ScienceAutumn 2020
- Extent and Intensity
- 0/1/0. 2 credit(s). Type of Completion: z (credit).
- Teacher(s)
- Mgr. Matej Kosiba, Ph.D. (seminar tutor)
Dr. Martin Topinka, PhD. (seminar tutor) - Guaranteed by
- Dr. Martin Topinka, PhD.
Department of Theoretical Physics and Astrophysics – Physics Section – Faculty of Science
Contact Person: Dr. Martin Topinka, PhD.
Supplier department: Department of Theoretical Physics and Astrophysics – Physics Section – Faculty of Science - Timetable
- Tue 17:00–18:50 Kontaktujte učitele
- Prerequisites (in Czech)
- Basics in programming in Python
- Course Enrolment Limitations
- The course is also offered to the students of the fields other than those the course is directly associated with.
- fields of study / plans the course is directly associated with
- there are 6 fields of study the course is directly associated with, display
- Course objectives (in Czech)
- The course serves as a non-mathematical introduction to the concept of Machine Learning. The students will get familiar with the state-of-art Machine Learning libraries in Python programming language and will be able to apply the learnt methods in various situations and tasks, with impact on the usage in astronomy.
- Learning outcomes (in Czech)
- Upon successfully completing the course, the student will be able to:
- understand the concept of Machine Learning
- understand and use several popular Machine Learning algorithms within the framework of the scikit-learn library for the Python programming language
understand the concept of deep learning and apply it in the framework of Keras /Tensorflow library
- define and complete a Machine Learning project of his/her own - Syllabus (in Czech)
- Introduction to Machine Learning, the idea of supervised, non-supervised learning, semi-supervised learning, Classification vs Regression
- General concept of Machine Learning, loss function
- Popular algorithms such as Support Vector Machine, Bayesian Regression, K-Nearest neighbours
- Data (feature) reduction such as Principal Component Analysis
- Practical use of scikit-learn Python library
- Model validation techniques. Fine-tuning model parameters.
- Principles of Deep Learning
- Practical use of Keras Deep Learning Python library
- Student's own project
- Teaching methods (in Czech)
- 50% of time lecturing, 50% practical exercise
- Language of instruction
- English
- Further Comments
- Study Materials
The course can also be completed outside the examination period.
The course is taught annually.
- Enrolment Statistics (Autumn 2020, recent)
- Permalink: https://is.muni.cz/course/sci/autumn2020/F5611