PlumX Metrics
Embed PlumX Metrics

Learning continuous models for continuous physics

Communications Physics, ISSN: 2399-3650, Vol: 6, Issue: 1
2023
  • 6
    Citations
  • 0
    Usage
  • 21
    Captures
  • 1
    Mentions
  • 0
    Social Media
Metric Options:   Counts1 Year3 Year

Metrics Details

  • Citations
    6
    • Citation Indexes
      6
  • Captures
    21
  • Mentions
    1
    • News Mentions
      1
      • News
        1

Most Recent News

New Findings in Physics Described from University of California (Learning continuous models for continuous physics)

2023 NOV 16 (NewsRx) -- By a News Reporter-Staff News Editor at Math Daily News -- Current study results on physics have been published. According

Article Description

Dynamical systems that evolve continuously over time are ubiquitous throughout science and engineering. Machine learning (ML) provides data-driven approaches to model and predict the dynamics of such systems. A core issue with this approach is that ML models are typically trained on discrete data, using ML methodologies that are not aware of underlying continuity properties. This results in models that often do not capture any underlying continuous dynamics—either of the system of interest, or indeed of any related system. To address this challenge, we develop a convergence test based on numerical analysis theory. Our test verifies whether a model has learned a function that accurately approximates an underlying continuous dynamics. Models that fail this test fail to capture relevant dynamics, rendering them of limited utility for many scientific prediction tasks; while models that pass this test enable both better interpolation and better extrapolation in multiple ways. Our results illustrate how principled numerical analysis methods can be coupled with existing ML training/testing methodologies to validate models for science and engineering applications.

Bibliographic Details

Aditi S. Krishnapriyan; Michael W. Mahoney; N. Benjamin Erichson; Alejandro F. Queiruga

Springer Science and Business Media LLC

Physics and Astronomy

Provide Feedback

Have ideas for a new metric? Would you like to see something else here?Let us know