In any data processing project that deals with personal information there is an inherent tradeoff between safeguarding data subjects’ privacy and yielding useful and accurate insights from the data.
The transparency of Artificial Intelligence (AI) models is an essential criterion for the deployment of AI in high-risk settings, such as medical applications. Consequently, numerous approaches for explaining AI systems have been proposed over the years (Samek et al., 2021).
L’intelligence artificielle (l’IA) soulève aussi bien des questionnements philosophiques qu’informatiques, chacun a sa petite idée au sujet des IA. Mais qu’en savons-nous vraiment?
The work "Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement", supported by iToBoS project, has been published.
Skin cancer is one of the most common cancers in the world. In the US alone, between 3 to 5 million new cases are reported each year, with treatment costs of approximately $9 billion.
The work "Measurably Stronger Explanation Reliability via Model Canonization", supported by iToBoS project, has been published.