convergence analysis 1gradient flow training 1inverse problems 1parametric problems 1residual neural networks 1
From the 1 of 3 linked papers with an AI index.
3 papers
math.NA2026
Approximation of solutions of parameter-dependent problems by residual neural networks
Ana Carpio
The paper introduces a simple training scheme for residual neural networks based on analytic activation functions and gradient flows, with convergence guaranteed by Lojasiewicz the…
cs.LG2025
Hierarchical topological clustering
Ana Carpio, Gema Duro
Topological methods have the potential of exploring data clouds without making assumptions on their the structure. Here we propose a hierarchical topological clustering algorithm t…
math.AP2025
Asymptotic models for the evolution of a circular biofilm
Diego Alonso-Orán, Ana Carpio, Rafael Granero-Belinchón
We study a class of lubrication-type equations modeling the spread of thin poroelastic biofilms at air/agar interfaces. Starting from a biofilm slab model, we perform a formal mult…