Learning and discovering multiple solutions using physics-informed neural networks with random initialization and deep ensemble

Documenti analoghi

• A comprehensive and FAIR comparison between MLP and KAN representations for differential equations and operator networks
  di: Shukla, Khemraj, et al.
  Pubblicazione: (2024)
• L-HYDRA: Multi-Head Physics-Informed Neural Networks
  di: Zou, Zongren, et al.
  Pubblicazione: (2023)
• Uncertainty Quantification in PINNs for Turbulent Flows: Bayesian Inference and Repulsive Ensembles
  di: Shukla, Khemraj, et al.
  Pubblicazione: (2026)
• Two-stage initial-value iterative physics-informed neural networks for simulating solitary waves of nonlinear wave equations
  di: Song, Jin, et al.
  Pubblicazione: (2024)
• Fast meta-solvers for 3D complex-shape scatterers using neural operators trained on a non-scattering problem
  di: Lee, Youngkyu, et al.
  Pubblicazione: (2024)