What is MF-VeBRNN?

| GitHub | Paper |

Summary

MF-VeBRNN provides the implementation for the paper Single-to-multi-fidelity history-dependent learning with uncertainty quantification and disentanglement: Application to data-driven constitutive modeling.

Statement of need

In the domain of data-driven modeling, there are different fidelities of data with different cost, accuracy, and noise. Data-driven learning is generalized to consider history-dependent multi-fidelity data, while quantifying epistemic uncertainty and disentangling it from data noise (aleatoric uncertainty). This generalization is hierarchical and adapts to different learning scenarios: from training the simplest single-fidelity deterministic neural networks up to the proposed multi-fidelity variance estimation Bayesian recurrent neural networks.

Authorship: - This repo is developed Jiaxiang Yi, a PhD researcher of Delft University of Technology, based on his research context.

Community Support

If you find any issues, bugs or problems with this package, please use the GitHub issue tracker to report them.

License

Copyright (c) 2025, Jiaxiang Yi

All rights reserved.

This project is licensed under the BSD 3-Clause License. See LICENSE for the full license text.