Machine Learning for Physicists and Astronomers
Wouldn't it be nice if the computer could learn how to best analyze your data automatically? It might not be that simple, but in this course you will learn about machine learning, how it can be used and its limitations. Focus is on applications in physics and astronomy.
Machine learning is one of the fastest growing and most dynamic areas of modern physics research and data application. In this course you will get an introduction to the core concepts, theory and tools of machine learning as required by physicists and astronomers addressing practical data analysis tasks. Use cases and limitations of machine learning algorithms will be discussed. The implementation and use of machine learning in practical applications will be exemplified, and realistic scenarios will be studied in applications relevant to physics research and astronomy.
This is a second cycle course given at half speed during daytime.
This course consists of two parts:
* Theory. In this part, the theory of machine learning and different models of it will be studied. You will also learn about how to choose which method for your given problem and the limitation of different methods.
* Project. In this part, you will implement and use machine learning for data analysis. You will also learn how to prepare data and train machine learning models and evaluate the performance and quality of them.
The teaching consists of lectures, group education and supervision of projects.
The theory part is examined by a written and oral exam. The project part is examined through a written and oral presentation of the project work.
Adam Andrews, e-mail: email@example.com
ScheduleThis is a preliminary schedule and is subject to continuous change. For this reason, we do not recommend print-outs. At the start of the course, your institution will advise where you can find your schedule during the course.
Course literatureNote that the course literature can be changed up to two months before the start of the course.
- Understanding Machine Learning: From Theory to Algorithms, Shai Ben-David and Shai Shalev-Shwartz, Cambridge University Press New York, NY, USA, 2014
- Pattern Recognition and Machine Learning (Information Science and Statistics), Christopher M. Bishop, Springer-Verlag Berlin, Heidelberg, 2006
- Deep Learning, Ian Goodfellow, Yoshua Bengio, Aaron Courville, The MIT Press, 2016
Note that online versions of the books are available for free.