A Library for Learning Neural Operators

שמור ב:

מידע ביבליוגרפי
הוצא לאור ב:	arXiv.org (Dec 17, 2024), p. n/a
מחבר ראשי:	Kossaifi, Jean
מחברים אחרים:	Kovachki, Nikola, Li, Zongyi, Pitt, David, Liu-Schiaffini, Miguel, George, Robert Joseph, Bonev, Boris, Azizzadenesheli, Kamyar, Berner, Julius, Anandkumar, Anima
יצא לאור:	Cornell University Library, arXiv.org
נושאים:	Learning curves Python Function space Convergence Neural networks Operators (mathematics) Discretization Open source software Euclidean geometry
גישה מקוונת:	Citation/Abstract Full text outside of ProQuest
תגים:	הוספת תג אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!

תיאור
Resumen:	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. Built on top of PyTorch, 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.
ISSN:	2331-8422
Fuente:	Engineering Database