/pml_workshops

Primary LanguageJupyter Notebook

Workshops by the Probabilistic Mechanics Laboratory

Welcome to the PML Workshop repository. We use this repository to disseminate the results of our research and make them accessible to the broader scientific community.

Content

The repository consists of the following Jupyter Notebooks:

1_simple_logistic_regression.ipynb:

  • The simplest model: perceptron
  • The basis of backpropagation: forward and backward passes
  • Multilayer perceptron

2_PINN_sciann_Burgers.ipynb:

  • Physics-informed neural networks
  • Basic concepts and formulation
  • Example using SciANN

3_hybrid_PINN.ipynb:

  • Hybrid models combining physics-informed kernels and neural networks
  • Cumulative damage example

Further reading

If you are interested in applied machine learning, physics-informed neural networks, and hybrid models, you might consider the following list of papers: