#learning #deep-learning #merging #mitigation #machine-learning #lighting #itu

Deep neural networks frequently encode and propagate biases arising from data, model design, and deployment contexts, posing significant challenges for reliable and lawful AI systems. This presentation surveys debiasing techniques for deep neural networks, situating them within the regulatory constraints introduced by the AI Act. We compare supervised and unsupervised debiasing methods, emphasizing their underlying assumptions, optimization objectives, and practical trade-offs. The talk then addresses bias discovery and bias naming as foundational problems for systematic bias mitigation. Finally, we discuss emerging research directions, including privacy-aware debiasing, fairness certification, and machine unlearning, highlighting open technical challenges and unresolved tensions between fairness, robustness, and compliance.

 

Bio: