Learning outcomes
Learning outcomes#
This course introduces the key concepts of machine learning, from the underlying mathematical foundations up to advanced implementations.
The context of examples and tutorials is taken from experimental particle physics.
No prerequisite in Physics needed!
Don’t worry if you do not know anything about particle physics! This is a mathematics course with a high component of hands-on programming tutorials. The exercises will be simplified and require no former physics prerequisites.
After this course you should be able to:
Derive the mathematics behind the machine learning’s basic algorithms
Identify and compare the common algorithms and architectures used in supervised and unsupervised learning
Implement a machine learning program in python performing classification from a dataset
Measure and improve the performance of a machine learning model using optimization tools
Build advanced architectures relevant to solve a problem from a dataset