Trustworthy Machine Learning Systems

What it is about

You learn how to design and evaluate systems that provide trustworthy functions with machine-learning components. In the end you will be able to assess the necessity, benefits and challenges of such systems in various application fields, as well as analyze risks and derive appropriate measures to create trustworthy ML components.

What you will be able to do

• Assessment of need, benefit and challenges of trustworthy systems with ML modules
• Understanding the relationship between trustworthy components and dependable functions
• Knowledge of the European AI Act and relevant standards
• Assessment of concerns when deploying ML in concrete applications
• Creation of appropriate risk analyses
• Knowledge of the dimensions of trustworthiness and basics for creating trustworthy ML-enabled systems

What the module consists of

• VorlesungDelivery of the structured content on trustworthiness, standards, risk analysis and architectures; discussions enriched with current 'trusted AI' news

Teaching method

• PräsentationStructured introduction of the content at the beginning of the lecture
• DiskussionInvolvement of students through guided questions and discussion of current developments, standards, products and problems for deeper understanding