1 citations · 1 across the 5 of their papers we have counts for
7 papers
Interior interpretability with attention rollout: contraction and propagation profiles in Transformers
Umberto Biccari, Qian Huang, Enrique Zuazua
Feature-attribution methods assign scores relating input variables to a model's output, but do not by themselves characterize how explicitly defined interaction operators compose a…
Robust stabilization of hyperbolic PDE-ODE systems via Neural Operator-approximated gain kernels
Kaijing Lyu, Umberto Biccari, Junmin Wang
This paper investigates the mean square exponential stabilization problem for a class of coupled PDE-ODE systems with Markov jump parameters. The considered system consists of mult…
Learning the Riccati solution operator for time-varying LQR via Deep Operator Networks
Jun Chen, Umberto Biccari, Junmin Wang
We propose a computational framework for replacing the repeated numerical solution of differential Riccati equations in finite-horizon Linear Quadratic Regulator (LQR) problems by…
Operator learning for prescribed-time stabilization of reaction-diffusion systems
Kaijing Lyu, Umberto Biccari, Jun-Min Wang
This paper addresses boundary prescribed-time stabilization of a one-dimensional heat equation with spatially and temporally varying coefficients. In contrast to asymptotic or expo…
Fair feature attribution for multi-output prediction: a Shapley-based perspective
Umberto Biccari, Alain Ibáñez de Opakua, José MarÃa Mato +3
In this article, we provide an axiomatic characterization of feature attribution for multi-output predictors within the Shapley framework. While SHAP explanations are routinely com…
Spiking Neural Networks: a theoretical framework for Universal Approximation and training
Umberto Biccari
Spiking Neural Networks (SNNs) are widely regarded as a biologically-inspired and energy-efficient alternative to classical artificial neural networks. Yet, their theoretical found…