Dr Federico Castagna
Lecturer in Computer Science

Topics

The following is a (non-exhaustive) list of research ideas I would be interested in pursuing.

• Ethics of AI: challenges and potential solutions.
• Explainable AI (XAI): developing methods and tools for addressing AI systems' black-box nature by enhancing their interpretability.
• Computational Argumentation: being a well-established formalisation of non-monotonic reasoning, computational argumentation is a tool suitable for handling inconsistent and conflicting information. I am interested in finding original applications for this approach, especially in relation to resource-bounded agent characterisation.