3 papers
math.NA2025
Cardiocirculatory Computational Models for the Study of Hypertension
Simone Celora, Andrea Tonini, Francesco Regazzoni +3
In this work, we develop patient-specific cardiocirculatory models with the aim of building Digital Twins for hypertension. In particular, in our pathophysiology-based framework, w…
math.NA2025
Improvements on uncertainty quantification with variational autoencoders
Andrea Tonini, Tan Bui-Thanh, Francesco Regazzoni +2
Inverse problems aim to determine model parameters of a mathematical problem from given observational data. Neural networks can provide an efficient tool to solve these problems. I…
cs.LG2025
Enhanced uncertainty quantification variational autoencoders for the solution of Bayesian inverse problems
Andrea Tonini, Luca Dede'
Among other uses, neural networks are a powerful tool for solving deterministic and Bayesian inverse problems in real-time, where variational autoencoders, a specialized type of ne…