Three Spanish researchers want AI to admit its uncertainty in critical decisions
Three Spanish researchers who have just won the BBVA Foundation's Leonardo Grant in Artificial Intelligence and Cognitive Science are working to make AI models convey uncertainty instead of answering with false confidence. Their projects address tumor image analysis, simulation of treatments for ICU patients and prediction of failures in power grid transformers, fields where an unflagged error can have serious consequences.
In 35 seconds
- Pablo Morales-Álvarez (UGR) uses Bayesian statistics so the system indicates the probability that a tumor is primary or metastatic.
- Cristina Soguero-Ruiz (URJC) develops digital twins to simulate ICU treatments with an associated confidence level.
- Joxe Aizpurua applies physics-guided machine learning to predict the useful life of grid transformers.
IASummary generated by artificial intelligence from a story by El Confidencial. It may contain errors: the original source prevails.
%3Aformat(jpg)%3Aquality(99)%3Awatermark(f.elconfidencial.com%2Ffile%2F65c%2F43d%2F0ca%2F65c43d0ca5dbd5ff8f19b44167343db9.png%2C0%2C275%2C1)%2Ff.elconfidencial.com%2Foriginal%2F282%2Fc3a%2Fb49%2F282c3ab49448843418f08bfabf701024.jpg&w=1200&q=75)



Comments
Be respectful. Comments reported by several people are hidden until a moderator reviews them.
You do not need an account to read, only to comment. Sign in with a code sent to your email or with your Google account. We only show the name you choose, never your email.