Energy Dissipation Preserving Feature-based DNN Galerkin Methods for Gradient Flows

Documenti analoghi

• Structured First-Layer Initialization Pre-Training Techniques to Accelerate Training Process Based on $\varepsilon$-Rank
  di: Tang, Tao, et al.
  Pubblicazione: (2025)
• $ε$-rank and the Staircase Phenomenon: New Insights into Neural Network Training Dynamics
  di: Yang, Jiang, et al.
  Pubblicazione: (2024)
• A Conservative and Positivity-Preserving Discontinuous Galerkin Method for the Population Balance Equation
  di: Xu, Ziyao, et al.
  Pubblicazione: (2025)
• Structure Preserving Polytopal Discontinuous Galerkin Methods for the Numerical Modeling of Neurodegenerative Diseases
  di: Corti, Mattia, et al.
  Pubblicazione: (2023)
• Higher-Order Energy-Decreasing Exponential Time Differencing Runge-Kutta methods for Gradient Flows
  di: Fu, Zhaohui, et al.
  Pubblicazione: (2024)