JuliusMartensen

I think this is related to the REPL (assuming you are using it here) and since we are reusing the `AbstractSystem` this falls back to [show](https://github.com/SciML/ModelingToolkit.jl/blob/8acf77483aa08508d7a45a937d343b4990a41d17/src/systems/abstractsystem.jl#L595).

Interesting! Just some drafts here: Either we define the `NeuralBasis` we talked about or we simply provide a function like ```julia function EDMD(X, NN, epochs, args...) # Init # Training...

I am sorry if I lost information in the progress. The change to `v0.6.0` is breaking, so the interface changed highly and until `v1.0` should not be considered stable. DMD...

> A is not documented in `sparse_regression!` Via #233

Thanks! I'll have a look into this! Most likely this could be done as an Algorithm ( and both methods can be implemented ).

Thanks for pointing this out. Would it be okay for you, if I adapt directly from the implementation in `ControlSystemIdentification`? Also, I was reading [this paper](https://arxiv.org/pdf/2005.04291.pdf) which is related and...

I've been thinking about this for a while now and would like to see this (GP/SR) as part of DataDrivenDiffEq. Either we reuse something already present, like [ExprOptimization](https://github.com/sisl/ExprOptimization.jl), and use...

After looking into #160, if think we can implement [FFX](https://www.researchgate.net/publication/225965816_FFX_Fast_Scalable_Deterministic_Symbolic_Regression_Technology) pretty fast.

Seems like it's related to the training loop of the ude. Have you tried running it from the terminal directly? Otherwise, the initial parameters of the network might have an...

I assume that this has to do with dependencies crashing with each other. The tagged version of MTK should not be dependent on Enzyme ( AFAIK - might have changed...