<link rel="stylesheet" href="styles.cf390c6bfbe7555f.css">

Radial basis operator networks

dc.contributor.authorKurz, Jason A.
dc.contributor.authorOughton, Sean
dc.contributor.authorLiu, S.
dc.contributor.editorYurish, Sergey Y.
dc.coverage.spatialConference held at Innsbruck, Austria
dc.date.accessioned2026-11-19T23:34:03Z
dc.date.issued2025
dc.description.abstractOperator networks are designed to approximate nonlinear operators, which map between infinite-dimensional spaces like function spaces. These networks are increasingly important in machine learning, particularly in scientific computing, due to their ability to handle data common in fields like climate modeling and fluid dynamics, where inputs are often discretized continuous fields (e.g., temperature or velocity distributions). We introduce the radial basis operator network (RBON), which represents a breakthrough as the first operator network capable of learning an operator in both the time and frequency domains when adjusted to accept complex-valued inputs. Despite the small, single hidden-layer structure, the RBON boasts small ܮଶ relative test error for both in- and out-of-distribution data (OOD) of less than 1 × 10ି଻ in some benchmark cases. Furthermore, it maintains small errors on OOD data from entirely different function classes than those used during training, showcasing its robustness and adaptability for advanced scientific applications.
dc.identifier.citationKurz, J., Oughton, S., & Liu, S. (2025). Radial basis operator networks. In S. Y. Yurish (Ed.), Proceedings of the 7th International Conference on Advances in Signal Processing and Artificial Intelligence (ASPAI' 2025), Innsbruck, Austria, 8-10 April 2025 (pp. 189-196). IFSA Publishing. https://doi.org/10.13140/RG.2.2.14725.46566
dc.identifier.doi10.13140/RG.2.2.14725.46566
dc.identifier.isbn978-84-09-71189-5
dc.identifier.issn2938-5350
dc.identifier.urihttps://hdl.handle.net/10289/18802
dc.language.isoen
dc.publisherIFSA Publishing
dc.relation.isPartOfProceedings of the 7th International Conference on Advances in Signal Processing and Artificial Intelligence (ASPAI' 2025)
dc.rightsThis is an accepted version of a paper presented at the 7th International Conference on Advances in Signal Processing and Artificial Intelligence (ASPAI' 2025). © 2025 IFSA Publishing. Used with permission.
dc.source7th International Conference on Advances in Signal Processing and Artificial Intelligence (ASPAI' 2025)
dc.subjectmachine learning
dc.subjectmathematics
dc.subjectneural operators
dc.subjectoperator networks
dc.subjectpartial differential equations
dc.subjectradial basis functions
dc.subjectscientific computing
dc.titleRadial basis operator networks
dc.typeConference Contribution
dspace.entity.typePublicationen
pubs.publisher-urlhttps://www.aspai-conference.com/aspai_2025_proceedings.html

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
2410.04639v3.pdf
Size:
492.68 KB
Format:
Adobe Portable Document Format
Description:
Accepted version