FMIFlux.jl is a free-to-use software library for the Julia programming language, which offers the ability to setup NeuralFMUs: You can place FMUs (fmi-standard.org) simply inside any feed-forward NN topology and still keep the resulting hybrid model trainable with a standard AD training process.

1. open a Julia-Command-Window, activate your prefered environemnt
2. goto package manager using ]
3. type add FMIFlux or add "https://github.com/ThummeTo/FMIFlux.jl"
4. have a look in the example folder

• building and training ME-NeuralFMUs with the default Flux-Front-End
• building and training CS-NeuralFMUs
• ...

• different modes for sensitivity estimation
• documentation
• more examples
• ...