Skip to content

Transformed Generative Pre-Trained Physics-Informed Neural Networks (TGPT-PINN), a framework that extends Physics-Informed Neural Networks (PINNs) and reduced basis methods (RBM) to the non- linear model reduction regime while maintaining the type of network structure and the unsupervised nature of its learning.

Notifications You must be signed in to change notification settings

DuktigYajie/TGPT-PINN

Repository files navigation

Transformed Generative Pre-Trained Physics-Informed Neural Networks

Transformed Generative Pre-Trained Physics-Informed Neural Networks (TGPT-PINN), a framework that extends Physics-Informed Neural Networks (PINNs) and reduced basis methods (RBM) to the non- linear model reduction regime while maintaining the type of network structure and the unsupervised nature of its learning.

TGPT-PINN: Nonlinear model reduction with transformed GPT-PINNs

Yanlai Chen, Yajie Ji, Akil Narayan, Zhenli Xu

Paper Links: arXiv | ResearchGate

Talk/Presentation: YouTube

TGPT-PINN Architecture

image

Citation:

Below you can find the Bibtex citation:

@article{chen2024tgpt,
   title={TGPT-PINN: Nonlinear model reduction with transformed GPT-PINNs},
   author={Chen, Yanlai and Ji, Yajie and Narayan, Akil and Xu, Zhenli},
   journal={arXiv preprint arXiv:2403.03459},
   year={2024}
}

About

Transformed Generative Pre-Trained Physics-Informed Neural Networks (TGPT-PINN), a framework that extends Physics-Informed Neural Networks (PINNs) and reduced basis methods (RBM) to the non- linear model reduction regime while maintaining the type of network structure and the unsupervised nature of its learning.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages