The workshop is divided into four parts:

Introduction to ML:
Foster a general ability to understand how machine learning works.
What is supervised and what is unsupervised learning?
Which requirements do we need to learn successfully?

Statistical Machine Learning:
Understand the concepts behind classical machine learning algorithms and their advantages over modern deep learning approaches.
We can discuss many aspects of feature engineering and data representation by implementing one specific method.

Neuronal Networks:
By taking on the same dataset as the previous session, we explore some strengths in neuronal network approaches. We build, train, and discuss results based on neuronal networks.

MLOps:
After talking about machine learning in general and building our models - it is time to talk about deployment.
We deploy a small container based on FastAPI and our previously trained models to expose an API endpoint for further development.