Cover Image

Improving physics-informed neural network extrapolation via transfer learning and adaptive activation functions

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Papastathopoulos-Katsaros, Athanasios, Stavrianidi, Alexandra, Liu, Zhandong
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Numerical Analysis Dynamical Systems
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Weak Collocation Regression for Inferring Stochastic Dynamics with Lévy Noise
by: Guo, Liya, et al.
Published: (2024)

Weak Collocation Regression method: fast reveal hidden stochastic dynamics from high-dimensional aggregate data
by: Lu, Liwei, et al.
Published: (2022)

A review of shape-morphing solutions and evolutional neural networks for spatiotemporal dynamics
by: Farazmand, Mohammad
Published: (2026)

Flexible SE(2) graph neural networks with applications to PDE surrogates
by: Bånkestad, Maria, et al.
Published: (2024)

When is a System Discoverable from Data? Discovery Requires Chaos
by: Shumaylov, Zakhar, et al.
Published: (2025)

CP-PINNs: Data-Driven Changepoints Detection in PDEs Using Online Optimized Physics-Informed Neural Networks
by: Dong, Zhikang, et al.
Published: (2022)

Learning phase-space flows using time-discrete implicit Runge-Kutta PINNs
by: Corral, Álvaro Fernández, et al.
Published: (2024)

Entropic transfer operators for stochastic systems
by: Bi, Hancheng, et al.
Published: (2025)

A matrix preconditioning framework for physics-informed neural networks based on adjoint method
by: Song, Jiahao, et al.
Published: (2025)

An extrapolation-driven network architecture for physics-informed deep learning
by: Wang, Yong, et al.
Published: (2024)

Numerical approximation of the Koopman-von Neumann equation: Operator learning and quantum computing
by: Klus, Stefan, et al.
Published: (2026)

Multi-Condition Digital Twin Calibration for Axial Piston Pumps : Compound Fault Simulation
by: Dong, Chang, et al.
Published: (2026)

Multi evolutional deep neural networks (Multi-EDNN)
by: Kim, Hadden, et al.
Published: (2024)

Efficient forward and inverse uncertainty quantification for dynamical systems based on dimension reduction and Kriging surrogate modeling in functional space
by: Song, Zhouzhou, et al.
Published: (2025)

Data-driven modelling of brain activity using neural networks, Diffusion Maps, and the Koopman operator
by: Gallos, Ioannis K., et al.
Published: (2023)

Development of multi-physics finite element model to investigate electromagnetic forming and simultaneous multi-point perforations of aluminium tube
by: Chetry, Avinash, et al.
Published: (2024)

Backpropagation in hyperbolic chaos via adjoint shadowing
by: Ni, Angxiu
Published: (2022)

Sparse identification of time delay systems via pseudospectral collocation
by: Bozzo, Enrico, et al.
Published: (2024)

Astral: training physics-informed neural networks with error majorants
by: Fanaskov, Vladimir, et al.
Published: (2024)

On the Higuchi fractal dimension of invariant measures for countable idempotent iterated function systems
by: Oliveira, Elismar R.
Published: (2024)

Kernel Methods for the Construction of Certified Lyapunov Functions via Approximate Koopman Eigenfunctions
by: Giesl, P., et al.
Published: (2026)

Joint State-Parameter Estimation for the Reduced Fracture Model via the United Filter
by: Huynh, Toan, et al.
Published: (2025)

Stochastic bifurcation analysis via polynomial chaos: consistency and convergence of branch-approximating solutions
by: Venier, Giacomo, et al.
Published: (2026)

Optimal Low-dimensional Approximation of Transfer Operators via Flow Matching: Computation and Error Analysis
by: Zhang, Zhicheng, et al.
Published: (2024)

Predicting nonlinear-flow regions in highly heterogeneous porous media using adaptive constitutive laws and neural networks
by: Giovannini, Chiara, et al.
Published: (2024)

Hutchinson Trace Estimation for High-Dimensional and High-Order Physics-Informed Neural Networks
by: Hu, Zheyuan, et al.
Published: (2023)

Score-Based Physics-Informed Neural Networks for High-Dimensional Fokker-Planck Equations
by: Hu, Zheyuan, et al.
Published: (2024)

Incorporating Continuous Dependence Qualifies Physics-Informed Neural Networks for Operator Learning
by: Li, Guojie, et al.
Published: (2026)

Calculating Domain of Attraction Boundary of Power Systems Based on the Gentlest Ascent Dynamics
by: Wu, Sixu, et al.
Published: (2026)

HomPINNs: homotopy physics-informed neural networks for solving the inverse problems of nonlinear differential equations with multiple solutions
by: Zheng, Haoyang, et al.
Published: (2023)

A kernel method for the learning of Wasserstein geometric flows
by: Hu, Jianyu, et al.
Published: (2025)

Data-driven approximation of transfer operators for mean-field stochastic differential equations
by: Ioannou, Eirini, et al.
Published: (2025)

Improving PINNs By Algebraic Inclusion of Boundary and Initial Conditions
by: Ren, Mohan, et al.
Published: (2024)

SPIKE: Sparse Koopman Regularization for Physics-Informed Neural Networks
by: Miñoza, Jose Marie Antonio
Published: (2026)

FMint: Bridging Human Designed and Data Pretrained Models for Differential Equation Foundation Model
by: Song, Zezheng, et al.
Published: (2024)

PI-Controlled Variable Time-Step Power System Simulation Using an Adaptive Order Differential Transformation Method
by: Huang, Kaiyang, et al.
Published: (2025)

Generalized Chebyshev Acceleration
by: Gökgöz, Nurgül
Published: (2025)

A CFL-type Condition and Theoretical Insights for Discrete-Time Sparse Full-Order Model Inference
by: Gkimisis, Leonidas, et al.
Published: (2025)

Parallelized computation of quasi-periodic solutions for finite element problems: A Fourier series expansion-based shooting method
by: Wu, Junqing, et al.
Published: (2025)

A step towards holistic discretisation of stochastic partial differential equations
by: Roberts, A. J.
Published: (2003)