A Library for Learning Neural Operators

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kossaifi, Jean, Kovachki, Nikola, Li, Zongyi, Pitt, David, Liu-Schiaffini, Miguel, George, Robert Joseph, Bonev, Boris, Azizzadenesheli, Kamyar, Berner, Julius, Duruisseaux, Valentin, Anandkumar, Anima
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914292252540928
author Kossaifi, Jean
Kovachki, Nikola
Li, Zongyi
Pitt, David
Liu-Schiaffini, Miguel
George, Robert Joseph
Bonev, Boris
Azizzadenesheli, Kamyar
Berner, Julius
Duruisseaux, Valentin
Anandkumar, Anima
author_facet Kossaifi, Jean
Kovachki, Nikola
Li, Zongyi
Pitt, David
Liu-Schiaffini, Miguel
George, Robert Joseph
Bonev, Boris
Azizzadenesheli, Kamyar
Berner, Julius
Duruisseaux, Valentin
Anandkumar, Anima
contents We present NeuralOperator, an open-source Python library for operator learning. Neural operators generalize neural networks to maps between function spaces instead of finite-dimensional Euclidean spaces. They can be trained and inferenced on input and output functions given at various discretizations, satisfying a discretization convergence properties. Part of the official PyTorch Ecosystem, NeuralOperator provides all the tools for training and deploying neural operator models, as well as developing new ones, in a high-quality, tested, open-source package. It combines cutting-edge models and customizability with a gentle learning curve and simple user interface for newcomers.
format Preprint
id arxiv_https___arxiv_org_abs_2412_10354
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Library for Learning Neural Operators
Kossaifi, Jean
Kovachki, Nikola
Li, Zongyi
Pitt, David
Liu-Schiaffini, Miguel
George, Robert Joseph
Bonev, Boris
Azizzadenesheli, Kamyar
Berner, Julius
Duruisseaux, Valentin
Anandkumar, Anima
Machine Learning
Artificial Intelligence
We present NeuralOperator, an open-source Python library for operator learning. Neural operators generalize neural networks to maps between function spaces instead of finite-dimensional Euclidean spaces. They can be trained and inferenced on input and output functions given at various discretizations, satisfying a discretization convergence properties. Part of the official PyTorch Ecosystem, NeuralOperator provides all the tools for training and deploying neural operator models, as well as developing new ones, in a high-quality, tested, open-source package. It combines cutting-edge models and customizability with a gentle learning curve and simple user interface for newcomers.
title A Library for Learning Neural Operators
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2412.10354