Neural Hybrid Automata tutorial

DiffEqML / torchdyn

A PyTorch library entirely dedicated to neural differential equations, implicit models and related numerical methods

https://torchdyn.org

Apache License 2.0

1.36k stars 125 forks source link

Neural Hybrid Automata tutorial #100

Open Zymrael opened 3 years ago

Zymrael commented 3 years ago

Tutorial for this paper. odeint_hybrid is already in.

@frankschae On our end, it would be good to extend the NHA tutorial with adjoint sensitivity through the events. ping since you're working on sensitivity + NHDE and you might be able to provide guidance on implementation tricks later on.

frankschae commented 3 years ago

awesome. I still have some issues with respect to the additional contributions for implicit event functions but I'll let you know once I figure it out. :)

frankschae commented 3 years ago

I think we have now all the terms, tried to summarize them/implementation steps in the post: https://frankschae.github.io/post/bouncing_ball/ The PR for BacksolveAdjoint is: https://github.com/SciML/DiffEqSensitivity.jl/pull/445