.png){kind=icon}
.png){kind=icon}
Return
Galactic Margin Machines: A physics-inspired framework for nonlinear classification
.png){kind=icon}
OA
AI
DOI：10.1016/j.asoc.2026.115857.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Introduces a physics-inspired classifier based on data-induced potential fields. • Learns geometry-aware nonlinear decision boundaries without predefined kernels. • Identifies a sparse set of influential samples termed support stars. • Provides interpretable decision structures through equipotential surfaces. • Demonstrates competitive performance on complex synthetic and real datasets.
Keywords:
Galactic Margin Machine
Potential-field learning
Interpretable machine learning
Sparse classification
Geometry-aware decision boundaries
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.6
Papers:
1.4W
Citations:
4.8W
Organization
No organization information available