HCAIM - Trustworthy AI

The HCAIM (Human-Centered AI Master) programme’s second module focuses on the second phase of the MLOps development cycle: Deployment. This second module follows the first Module A – Modelling. This module enhances the complexity of AI technology by moving towards (the use of) neural networks and deep learning. The module focuses on making the deployment of AI solutions more transparent in order to identify and mitigate the risks associated.
The Ethical Focus lesson plan on Trustworthy AI combines lectures, tutorials, and practical sessions. The course begins by introducing General Explainable AI with practical sessions on XAI models and a lecture on cutting-edge XAI developments. The course then dives into Privacy (privacy and risk, perspectives on privacy, auditing privacy and data protection, privacy and machine learning, and evaluations of privacy-preserving techniques), followed by a section on Security and Robustness (including a practical session on applying auditing frameworks and enhancing ML security and robustness). Finally, the lecture concludes by going into Risk and Risk mitigation.
The module is designed to provide students with the necessary skills to evaluate correctly the direction of AI development and its future impacts on society and individuals. For more information, students can visit the HCAIM consortium’s homepage.