You can't operate machine learning systems well if you don't understand what they are made of. Python is the language almost every ML tool is built around, and a working grasp of how models are trained, evaluated, and used for inference is what lets you reason about everything that comes after.
You'll start with the basics of Python, then get a high-level picture of how machine learning works. From there the module moves to hands-on tooling: scikit-learn for classic models, preprocessing, and metrics, and PyTorch for deep learning.
You are not aiming to become a researcher here. The goal is to know enough about the model lifecycle to package, version, deploy, and monitor it, which is exactly what the next module, Linux, Git & DVC, starts to build on.
A fast tour of Python and why it became the default language for data science and machine learning work.
A short overview of what machine learning is: how models learn patterns from data instead of following hand-written rules.
A hands-on, beginner-focused course from freeCodeCamp on building models with scikit-learn and managing real machine learning projects. This is a long course, so treat it as a reference to dip into rather than something to watch in one sitting.
A quick introduction to PyTorch, the deep learning framework you'll meet again when training and serving models.