ChrisRackauckas / universal_differential_equations

Repository for the Universal Differential Equations for Scientific Machine Learning paper, describing a computational basis for high performance SciML
https://arxiv.org/abs/2001.04385
MIT License
220 stars 59 forks source link

outdated / soon to be outdated example codes #41

Open ghost opened 2 years ago

ghost commented 2 years ago

The code for the sindy to equations parts of the examples are out of date and won't run. In addition, running the SEIR model, the following warnings came up: FastChain is being deprecated in favor of Lux.jl sciml_train is being deprecated in favor of direct usage of Optimization.jl Seems like these examples will soon be outdated, but they're really useful.

ChrisRackauckas commented 2 years ago

My plan is to just add them to the SciMLSensitivity docs so they keep updated (and are part of the docs). It's blocked by needing more compute (https://github.com/SciML/SciMLSensitivity.jl/pull/674), but I'll get to that rather soon.