Graph Convolutional Neural Networks as Parametric CoKleisli morphisms

no code implementations • 1 Dec 2022 • Bruno Gavranović, Mattia Villani

We define the bicategory of Graph Convolutional Neural Networks $\mathbf{GCNN}_n$ for an arbitrary graph with $n$ nodes.

Inductive Bias

Feature Importance for Time Series Data: Improving KernelSHAP

no code implementations • 5 Oct 2022 • Mattia Villani, Joshua Lockhart, Daniele Magazzeni

Feature importance techniques have enjoyed widespread attention in the explainable AI literature as a means of determining how trained machine learning models make their predictions.

Event Detection Feature Importance +2

Low-energy electromagnetic processes affecting free-falling test-mass charging for LISA and future space interferometers

no code implementations • 4 Dec 2020 • Catia Grimani, Andrea Cesarini, Michele Fabi, Mattia Villani

In this paper, low-energy electromagnetic processes to be included in the future Monte Carlo simulations for LISA and LISA-like space interferometers TM charging are considered.

Space Physics