Introduction to AI - Machine Learning
1,5 credits, course, bachelor's level, D0050E
Summer 2026
Machine Learning powers the most capable AI systems in the world—from medical image analysis to recommendation engines and language technologies.
“Introduction to AI – Machine Learning” is a focused, practical dive into the models, workflows, and tools that make ML useful in everyday projects. You will learn how to turn a question into a dataset and a dataset into a model, compare classical and modern approaches, and interpret model performance with the right metrics. Through guided labs and demonstrations, you’ll practice selecting algorithms for classification and regression, setting up evaluation pipelines, and avoiding common pitfalls like data leakage and overfitting. We also discuss responsible ML: bias, privacy, transparency, and how to communicate uncertainty to stakeholders. The course is self-paced, offered in English, and structured for busy schedules with two live sessions for Q&A and peer exchange. Assessment centres on a reflective write-up and a mini-project connected to your own context—so the skills you gain transfer immediately. With 1.5 ECTS and a recommended prerequisite of “Introduction to AI – Basic” (or an equivalent such as Elements of AI), this course is ideal for learners who want confidence building and using ML responsibly and effectively in real applications. Come ready to experiment; we supply the structure, guidance, and modern tooling.
You will learn
Self-paced + two live sessions; reflective write-up and mini-project.
Who is it for? Learners ready to apply ML in real contexts.
You will learn
- Proper data prep, feature choice, and splits.
- Comparing models (linear, trees, ensembles) and reading metrics with confidence.
- Cross-validation, baselines, ablation, error analysis.
- Responsible ML: documentation, bias checks, privacy, communicating uncertainty.
Self-paced + two live sessions; reflective write-up and mini-project.
Who is it for? Learners ready to apply ML in real contexts.
1,5 credits, course, bachelor's level, D0050E
Summer 2026
Machine Learning powers the most capable AI systems in the world—from medical image analysis to recommendation engines and language technologies.
“Introduction to AI – Machine Learning” is a focused, practical dive into the models, workflows, and tools that make ML useful in everyday projects. You will learn how to turn a question into a dataset and a dataset into a model, compare classical and modern approaches, and interpret model performance with the right metrics. Through guided labs and demonstrations, you’ll practice selecting algorithms for classification and regression, setting up evaluation pipelines, and avoiding common pitfalls like data leakage and overfitting. We also discuss responsible ML: bias, privacy, transparency, and how to communicate uncertainty to stakeholders. The course is self-paced, offered in English, and structured for busy schedules with two live sessions for Q&A and peer exchange. Assessment centres on a reflective write-up and a mini-project connected to your own context—so the skills you gain transfer immediately. With 1.5 ECTS and a recommended prerequisite of “Introduction to AI – Basic” (or an equivalent such as Elements of AI), this course is ideal for learners who want confidence building and using ML responsibly and effectively in real applications. Come ready to experiment; we supply the structure, guidance, and modern tooling.
You will learn
Self-paced + two live sessions; reflective write-up and mini-project.
Who is it for? Learners ready to apply ML in real contexts.
You will learn
- Proper data prep, feature choice, and splits.
- Comparing models (linear, trees, ensembles) and reading metrics with confidence.
- Cross-validation, baselines, ablation, error analysis.
- Responsible ML: documentation, bias checks, privacy, communicating uncertainty.
Self-paced + two live sessions; reflective write-up and mini-project.
Who is it for? Learners ready to apply ML in real contexts.
Updated: