Imagen de Portada

A comprehensive and FAIR comparison between MLP and KAN representations for differential equations and operator networks

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Shukla, Khemraj, Toscano, Juan Diego, Wang, Zhicheng, Zou, Zongren, Karniadakis, George Em
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Computational Physics
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Learning and discovering multiple solutions using physics-informed neural networks with random initialization and deep ensemble
por: Zou, Zongren, et al.
Publicado: (2025)

Uncertainty Quantification in PINNs for Turbulent Flows: Bayesian Inference and Repulsive Ensembles
por: Shukla, Khemraj, et al.
Publicado: (2026)

NeuroSEM: A hybrid framework for simulating multiphysics problems by coupling PINNs and spectral elements
por: Shukla, Khemraj, et al.
Publicado: (2024)

L-HYDRA: Multi-Head Physics-Informed Neural Networks
por: Zou, Zongren, et al.
Publicado: (2023)

GIMLET: Generalizable and Interpretable Model Learning through Embedded Thermodynamics
por: Shiratori, Suguru, et al.
Publicado: (2025)

HJ-sampler: A Bayesian sampler for inverse problems of a stochastic process by leveraging Hamilton-Jacobi PDEs and score-based generative models
por: Meng, Tingwei, et al.
Publicado: (2024)

GMC-PINNs: A new general Monte Carlo PINNs method for solving fractional partial differential equations on irregular domains
por: Wang, Shupeng, et al.
Publicado: (2024)

Tackling the Curse of Dimensionality with Physics-Informed Neural Networks
por: Hu, Zheyuan, et al.
Publicado: (2023)

GRAFT-ATHENA: Self-Improving Agentic Teams for Autonomous Discovery and Evolutionary Numerical Algorithms
por: Toscano, Juan Diego, et al.
Publicado: (2026)

KKANs: Kurkova-Kolmogorov-Arnold Networks and Their Learning Dynamics
por: Toscano, Juan Diego, et al.
Publicado: (2024)

FMEnets: Flow, Material, and Energy networks for non-ideal plug flow reactor design
por: Wu, Chenxi, et al.
Publicado: (2025)

Leveraging Hamilton-Jacobi PDEs with time-dependent Hamiltonians for continual scientific machine learning
por: Chen, Paula, et al.
Publicado: (2023)

Quantification of total uncertainty in the physics-informed reconstruction of CVSim-6 physiology
por: De Florio, Mario, et al.
Publicado: (2024)

Optimizing the Optimizer for Physics-Informed Neural Networks and Kolmogorov-Arnold Networks
por: Kiyani, Elham, et al.
Publicado: (2025)

From PINNs to PIKANs: Recent Advances in Physics-Informed Machine Learning
por: Toscano, Juan Diego, et al.
Publicado: (2024)

ATHENA: Agentic Team for Hierarchical Evolutionary Numerical Algorithms
por: Toscano, Juan Diego, et al.
Publicado: (2025)

Learning in PINNs: Phase transition, total diffusion, and generalization
por: Anagnostopoulos, Sokratis J., et al.
Publicado: (2024)

Retrofitting Earth System Models with Cadence-Limited Neural Operator Updates
por: Bora, Aniruddha, et al.
Publicado: (2025)

Fast meta-solvers for 3D complex-shape scatterers using neural operators trained on a non-scattering problem
por: Lee, Youngkyu, et al.
Publicado: (2024)

H3PC: Hypersonic, High-Order, High-Performance Code with Adaptive Mesh Refinement and Real Chemistry
por: Peyvan, Ahmad, et al.
Publicado: (2025)

Leveraging viscous Hamilton-Jacobi PDEs for uncertainty quantification in scientific machine learning
por: Zou, Zongren, et al.
Publicado: (2024)

Body-Free Simulation of Three-Dimensional Turbulent Cylinder Wakes
por: Wang, Zhicheng, et al.
Publicado: (2025)

Scalable Bayesian Physics-Informed Kolmogorov-Arnold Networks
por: Gao, Zhiwei, et al.
Publicado: (2025)

Agentic Risk-Aware Set-Based Engineering Design
por: Kumar, Varun, et al.
Publicado: (2026)

Representation Meets Optimization: Training PINNs and PIKANs for Gray-Box Discovery in Systems Pharmacology
por: Daryakenari, Nazanin Ahmadi, et al.
Publicado: (2025)

A Variational Framework for Residual-Based Adaptivity in Neural PDE Solvers and Operator Learning
por: Toscano, Juan Diego, et al.
Publicado: (2025)

Inferring turbulent velocity and temperature fields and their statistics from Lagrangian velocity measurements using physics-informed Kolmogorov-Arnold Networks
por: Toscano, Juan Diego, et al.
Publicado: (2024)

Operator Learning for Reconstructing Flow Fields from Sparse Measurements: a Language Model Approach
por: Zhang, Qian, et al.
Publicado: (2026)

Toward Autonomous Engineering Design: A Knowledge-Guided Multi-Agent Framework
por: Kumar, Varun, et al.
Publicado: (2025)

Connecting the geometry and dynamics of many-body complex systems with message passing neural operators
por: Gabriel, Nicholas A., et al.
Publicado: (2025)

KAN or MLP: A Fairer Comparison
por: Yu, Runpeng, et al.
Publicado: (2024)

Learning Turbulent Flows with Generative Models: Super-resolution, Forecasting, and Sparse Flow Reconstruction
por: Oommen, Vivek, et al.
Publicado: (2025)

PowerMLP: An Efficient Version of KAN
por: Qiu, Ruichen, et al.
Publicado: (2024)

Deep Neural networks for solving high-dimensional parabolic partial differential equations
por: Zhang, Wenzhong, et al.
Publicado: (2026)

DeepVIVONet: Using deep neural operators to optimize sensor locations with application to vortex-induced vibrations
por: Wan, Ruyin, et al.
Publicado: (2025)

Spectral bias in physics-informed and operator learning: Analysis and mitigation guidelines
por: Khodakarami, Siavash, et al.
Publicado: (2026)

Curvature-Aware Optimization for High-Accuracy Physics-Informed Neural Networks
por: Jnini, Anas, et al.
Publicado: (2026)

UFO: A Domain-Unification-Free Operator Framework for Generalized Operator Learning
por: Qiao, Hanli, et al.
Publicado: (2026)

DeepSeek vs. ChatGPT vs. Claude: A Comparative Study for Scientific Computing and Scientific Machine Learning Tasks
por: Jiang, Qile, et al.
Publicado: (2025)

Fusion-DeepONet: A Data-Efficient Neural Operator for Geometry-Dependent Hypersonic and Supersonic Flows
por: Peyvan, Ahmad, et al.
Publicado: (2025)