Copertina

A Family of Adaptive Activation Functions for Mitigating Failure Modes in Physics-Informed Neural Networks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Murari, Krishna
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

FP64 is All You Need: Rethinking Failure Modes in Physics-Informed Neural Networks
di: Xu, Chenhui, et al.
Pubblicazione: (2025)

Physical Activation Functions (PAFs): An Approach for More Efficient Induction of Physics into Physics-Informed Neural Networks (PINNs)
di: Abbasi, Jassem, et al.
Pubblicazione: (2022)

ProPINN: Demystifying Propagation Failures in Physics-Informed Neural Networks
di: Wu, Haixu, et al.
Pubblicazione: (2025)

Learnable Activation Functions in Physics-Informed Neural Networks for Solving Partial Differential Equations
di: Farea, Afrah, et al.
Pubblicazione: (2024)

Functional Tensor Decompositions for Physics-Informed Neural Networks
di: Vemuri, Sai Karthikeya, et al.
Pubblicazione: (2024)

Approximating Families of Sharp Solutions to Fisher's Equation with Physics-Informed Neural Networks
di: Rohrhofer, Franz M., et al.
Pubblicazione: (2024)

Physics-Informed Neural Networks: Minimizing Residual Loss with Wide Networks and Effective Activations
di: Dashtbayaz, Nima Hosseini, et al.
Pubblicazione: (2024)

Understanding the Failure Modes of Transformers through the Lens of Graph Neural Networks
di: Lee, Hunjae
Pubblicazione: (2025)

Quantile Activation: Correcting a Failure Mode of ML Models
di: Challa, Aditya, et al.
Pubblicazione: (2024)

Scalable Quantum Error Mitigation with Physically Informed Graph Neural Networks
di: Wang, Huaxin, et al.
Pubblicazione: (2026)

ENN: A Neural Network with DCT Adaptive Activation Functions
di: Martinez-Gost, Marc, et al.
Pubblicazione: (2023)

DiGRAF: Diffeomorphic Graph-Adaptive Activation Function
di: Mantri, Krishna Sri Ipsit, et al.
Pubblicazione: (2024)

Mask-PINNs: Mitigating Internal Covariate Shift in Physics-Informed Neural Networks
di: Jiang, Feilong, et al.
Pubblicazione: (2025)

Diagnosing Failure Modes of Neural Operators Across Diverse PDE Families
di: Shikhman, Lennon
Pubblicazione: (2026)

Self-Adaptive Physics-Informed Neural Networks using a Soft Attention Mechanism
di: McClenny, Levi, et al.
Pubblicazione: (2020)

Non-Invasive Reconstruction of Cardiac Activation Dynamics Using Physics-Informed Neural Networks
di: Dermul, Nathan, et al.
Pubblicazione: (2026)

A Simple Spectral Failure Mode for Graph Convolutional Networks
di: Priebe, Carey E., et al.
Pubblicazione: (2020)

Conformalized Physics-Informed Neural Networks
di: Podina, Lena, et al.
Pubblicazione: (2024)

Physics-Informed Neural Network Approaches for Sparse Data Flow Reconstruction of Unsteady Flow Around Complex Geometries
di: Malineni, Vamsi Sai Krishna, et al.
Pubblicazione: (2025)

Parallel-in-Time Solutions with Random Projection Neural Networks
di: Betcke, Marta M., et al.
Pubblicazione: (2024)

Risk Management for Mitigating Benchmark Failure Modes: BenchRisk
di: McGregor, Sean, et al.
Pubblicazione: (2025)

AB-PINNs: Adaptive-Basis Physics-Informed Neural Networks for Residual-Driven Domain Decomposition
di: Botvinick-Greenhouse, Jonah, et al.
Pubblicazione: (2025)

SmartMixed: A Two-Phase Training Strategy for Adaptive Activation Function Learning in Neural Networks
di: Omidvar, Amin
Pubblicazione: (2025)

Data-Driven Adaptive PID Control Based on Physics-Informed Neural Networks
di: Ito, Junsei, et al.
Pubblicazione: (2025)

Resilient Graph Neural Networks: A Coupled Dynamical Systems Approach
di: Eliasof, Moshe, et al.
Pubblicazione: (2023)

PINNfluence: Influence Functions for Physics-Informed Neural Networks
di: Naujoks, Jonas R., et al.
Pubblicazione: (2024)

BOOST: Out-of-Distribution-Informed Adaptive Sampling for Bias Mitigation in Stylistic Convolutional Neural Networks
di: Vijendran, Mridula, et al.
Pubblicazione: (2025)

Topology-Aware Activation Functions in Neural Networks
di: Snopov, Pavel, et al.
Pubblicazione: (2025)

naPINN: Noise-Adaptive Physics-Informed Neural Networks for Recovering Physics from Corrupted Measurement
di: Kim, Hankyeol, et al.
Pubblicazione: (2026)

Preconditioning for Physics-Informed Neural Networks
di: Liu, Songming, et al.
Pubblicazione: (2024)

Complex Physics-Informed Neural Network
di: Si, Chenhao, et al.
Pubblicazione: (2025)

Physics-Informed Neural Networks and Extensions
di: Raissi, Maziar, et al.
Pubblicazione: (2024)

PINNs Failure Modes are Overfitting
di: Andersen, Nigel T., et al.
Pubblicazione: (2026)

Extension of Symmetrized Neural Network Operators with Fractional and Mixed Activation Functions
di: Santos, Rômulo Damasclin Chaves dos, et al.
Pubblicazione: (2025)

Leveraging Influence Functions for Resampling Data in Physics-Informed Neural Networks
di: Naujoks, Jonas R., et al.
Pubblicazione: (2025)

Fourier Feature Pyramids for Physics-Informed Neural Networks
di: Zhao, Brandon, et al.
Pubblicazione: (2026)

Physical Informed Neural Networks for modeling ocean pollutant
di: Battina, Karishma, et al.
Pubblicazione: (2025)

Architectural Strategies for the optimization of Physics-Informed Neural Networks
di: Saratchandran, Hemanth, et al.
Pubblicazione: (2024)

The Challenges of the Nonlinear Regime for Physics-Informed Neural Networks
di: Bonfanti, Andrea, et al.
Pubblicazione: (2024)

Trainable Adaptive Activation Function Structure (TAAFS) Enhances Neural Network Force Field Performance with Only Dozens of Additional Parameters
di: Li, Enji
Pubblicazione: (2024)