Computational Science
物理信息 Kolmogorov–Arnold 网络
Physics-informed Kolmogorov–Arnold networkA deep learning architecture that integrates physical laws and constraints into the Kolmogorov–Arnold representation to solve inverse problems with improved stability and accuracy. / 一种深度学习架构，将物理定律和约束整合到 Kolmogorov–Arnold 表示中，以解决具有改进稳定性和准确性的反演问题。
- Knowledge type
- 工艺技术
- First proposed or discovered
- Proposer
- Turkey Farm member
- Creator
- 农场主
- Last updated
- 2026-11-08 22:05:33
Sub-knowledge points
Kolmogorov–Arnold representationpositivity-constrained neural networkssource-intensity inversionnuclear contaminant transport
Higher-order knowledge points
No connected node yet
Main parameters and performance indicators
positivity constraint: ensures non-negative output valuesphysics-informed loss: integrates governing equations into the training objective
Open problems
No unresolved problem recorded yet
Related literature
ranked by community starsA positivity-constrained physics-informed Kolmogorov–Arnold network for stability-oriented source-intensity inversion in nuclear contaminant transportOpen source
Related products and links
No item recorded yet
Creation and modification trail
1 recordsRecord title: Physics-informed Kolmogorov–Arnold network.
Node update feedback
review required