A continuous convolutional trainable filter for modelling unstructured data

Convolutional Neural Network (CNN) is one of the most important architectures in deep learning. The fundamental building block of a CNN is a trainable filter, represented as a discrete grid, used to perform convolution on discrete input data. In this work, we propose a continuous version of a traina...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Computational mechanics 2023-08, Vol.72 (2), p.253-265
Hauptverfasser:	Coscia, Dario, Meneghetti, Laura, Demo, Nicola, Stabile, Giovanni, Rozza, Gianluigi
Format:	Artikel
Sprache:	eng
Schlagworte:	Approximation Artificial neural networks Classical and Continuum Physics Computational Science and Engineering Deep learning Domains Engineering Informatics Machine learning Mechanics Neural networks Original Paper Theoretical and Applied Mechanics Unstructured data
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!