Transformer PhysX is a Python packaged modeled after the Hugging Face repository designed for the use of transformers for modeling physical systems. Transformers have seen recent success in both natural language processing and vision fields but have yet to fully permute other machine learning areas. Originally proposed in Transformers for Modeling Physical Systems, this projects goal is to make these deep learning advances including self-attention and Koopman embeddings more accessible for the scientific machine learning community.

Documentation | Getting Started | Data

Transformers for Modeling Physical Systems [ ArXiV ] [ Neural Networks ]

	Embedding Model	Transformer
Lorenz
Cylinder Flow
Gray-Scott	-	-
Rossler

• Huggingface Repository
• Transformer illustrated blog post
• Deep learning Koopman dynamics blog post

Open an issue on the Github repository if you have any questions/concerns.

Find this useful or like this work? Cite us with:

@article{geneva2022transformers,
    title = {Transformers for modeling physical systems},
    author = {Nicholas Geneva and Nicholas Zabaras},
    journal = {Neural Networks},
    volume = {146},
    pages = {272-289},
    year = {2022},
    issn = {0893-6080},
    doi = {10.1016/j.neunet.2021.11.022},
    url = {https://www.sciencedirect.com/science/article/pii/S0893608021004500}
}