DiffEqFlux.jl
DiffEqFlux.jl copied to clipboard
SciML
Pre-built implicit layer architectures with O(1) backprop, GPUs, and stiff+non-stiff DE solvers, demonstrating scientific machine learning (SciML) and physics-informed machine learning methods
## Checklist - [ ] Appropriate tests were added - [ ] Any code changes were done in a way that does not break public API - [ ] All...
This pull request changes the compat entry for the `OptimizationPolyalgorithms` package from `0.2` to `0.2, 0.3` for package docs. This keeps the compat entries for earlier versions. Note: I have...
![github-actions[bot] avatar](https://avatars.githubusercontent.com/in/15368?v=4 "github-actions[bot] avatar"){kind=avatar}
This pull request changes the compat entry for the `Optimization` package from `3.9` to `3.9, 4` for package docs. This keeps the compat entries for earlier versions. Note: I have...
CompatHelper: bump compat for OptimizationOptimisers to 0.3 for package docs, (keep existing compat)
This pull request changes the compat entry for the `OptimizationOptimisers` package from `0.2` to `0.2, 0.3` for package docs. This keeps the compat entries for earlier versions. Note: I have...
This pull request changes the compat entry for the `OptimizationOptimJL` package from `0.2, 0.3` to `0.2, 0.3, 0.4` for package docs. This keeps the compat entries for earlier versions. Note:...
## Checklist - [NO] Appropriate tests were added - [YES] Any code changes were done in a way that does not break public API - [-] All documentation related to...
- In [Weather forecasting example,](https://docs.sciml.ai/DiffEqFlux/stable/examples/neural_ode_weather_forecast/#Weather-forecasting-with-neural-ODEs) you choose the `sum(abs2)` as the loss function, but in [Sebastian Callh personal blog](https://sebastiancallh.github.io/), he use the `Flux.mse` as the loss function. And the difference...
This pull request changes the compat entry for the `ForwardDiff` package from `0.10` to `0.10, 1` for package docs. This keeps the compat entries for earlier versions. Note: I have...
## Checklist - [ ] Appropriate tests were added - [ ] Any code changes were done in a way that does not break public API - [ ] All...
I am new to neural differential equations and have been going through some tutorials to better understand them. I noticed that in Python's [Diffrax tutorial](https://docs.kidger.site/diffrax/examples/neural_ode/), they use a batching scheme...
