Workshop “Transparency in AI” at the IQZ Kaiserslautern
The IQZ workshop “Transparency in AI: From Bias Awareness to Documentation Practices” at IQZ Kaiserslautern opens a series of workshops on the trustworthiness of AI systems. At a time when AI is increasingly being used in critical areas such as medicine, undetected decision biases are one of the biggest obstacles to its safe use.
The European AI Regulation responds to this with comprehensive transparency requirements for AI providers. However, it is not only developers who are required to comply - users also benefit from a sound understanding of transparency aspects when selecting and integrating AI solutions. This workshop offers a practice-oriented introduction and teaches best practices for the secure implementation and documentation of AI systems.
What you can expect:
In-depth insights into the opportunities and challenges of AI documentation
Best practices for the implementation and selection of trustworthy AI systems
The latest on transparency requirements of the European AI regulation
Strategies for detecting and handling bias in AI systems
The workshop will be held in English. Participation is free of charge.
Event Details
Date
30. Februar 2025
Time
1:45 pm — 5:30 pm
Target Audience
Managers, entrepreneurs, AI decision-makers from the industry
Location
Innovations & Qualitätszentrum
Deutsches Forschungszentrum für Künstliche Intelligenz
Trippstadter Str. 122
67663 Kaiserslautern
Target Audience
Managers, entrepreneurs and AI developers and users from industry
Speaker
Jana Fehr (Berlin Institute of Health at Charité)
Ludger van Elst
David Dembinsky
Hiba Najar (alle DFKI Kaiserslautern)
Agenda
01
TAI 101: A Brief Introduction to Trustworthy AI
Trustworthy AI Basics: Building a Common Ground
02
AI Transparency for Trustworthiness
Unmasking Bias: Dangers & Pitfalls
Exploring the Meaning of AI Transparency
Best Practices for Transparent AI through Documentation
Effective AI Documentation – State-of-the-Art
03
Transparency Beyond Documentation
Overview on Challenges & Opportunities of Explainable AI
Importance of Quality Metrics
