SimpleDiffEq.jl
NeuralPDE.jl
SimpleDiffEq.jl | NeuralPDE.jl | |
---|---|---|
1 | 10 | |
22 | 905 | |
- | 1.4% | |
5.9 | 9.7 | |
7 days ago | 1 day ago | |
Julia | Julia | |
GNU General Public License v3.0 or later | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
SimpleDiffEq.jl
-
Tutorials for Learning Runge-Kutta Methods with Julia?
There you go, that's one step of it, taken from SimpleDiffEq.jl. But that's a really bad method and should almost never be used in practice.
NeuralPDE.jl
-
Automatically install huge number of dependency?
The documentation has a manifest associated with it: https://docs.sciml.ai/NeuralPDE/dev/#Reproducibility. Instantiating the manifest will give you all of the exact versions used for the documentation build (https://github.com/SciML/NeuralPDE.jl/blob/gh-pages/v5.7.0/assets/Manifest.toml). You just ]instantiate folder_of_manifest. Or you can use the Project.toml.
-
from Wolfram Mathematica to Julia
PDE solving libraries are MethodOfLines.jl and NeuralPDE.jl. NeuralPDE is very general but not very fast (it's a limitation of the method, PINNs are just slow). MethodOfLines is still somewhat under development but generates quite fast code.
-
IA et Calcul scientifique dans Kubernetes avec le langage Julia, K8sClusterManagers.jl
GitHub - SciML/NeuralPDE.jl: Physics-Informed Neural Networks (PINN) and Deep BSDE Solvers of Differential Equations for Scientific Machine Learning (SciML) accelerated simulation
-
[D] ICLR 2022 RESULTS ARE OUT
That doesn't mean there's no use case for PINNs, we wrote a giant review-ish kind of thing on NeuralPDE.jl to describe where PINNs might be useful. It's just... not the best for publishing. It's things like, (a) where you have not already optimized a classical method, (b) need something that's easy to generate solvers for different cases without too much worry about stability, (c) high dimensional PDEs, and (d) surrogates over parameters. (c) and (d) are the two "real" uses cases you can actually publish about, but they aren't quite good for (c) (see mesh-free methods from the old radial basis function literature in comparison) or (d) (there are much faster surrogate techniques). So we are continuing to work on them for (a) and (b) as an interesting option as part of a software suite, but that's not the kind of thing that's really publishable so I don't think we plan to ever submit that article anywhere.
- [N] Open Colloquium by Prof. Max Welling: "Is the next deep learning disruption in the physical sciences?"
-
[D] What are some ideas that are hyped up in machine learning research but don't actually get used in industry (and vice versa)?
Did this change at all with the advent of Physics Informed Neural Networks? The Julia language has some really impressive tools for that use case. https://github.com/SciML/NeuralPDE.jl
-
[Research] Input Arbitrary PDE -> Output Approximate Solution
PDEs are difficult because you don't have a simple numerical definition over all PDEs because they can be defined by arbitrarily many functions. u' = Laplace u + f? Define f. u' = g(u) * Laplace u + f? Define f and g. Etc. To cover the space of PDEs you have to go symbolic at some point, and make the discretization methods dependent on the symbolic form. This is precisely what the ModelingToolkit.jl ecosystem is doing. One instantiation of a discretizer on this symbolic form is NeuralPDE.jl which takes a symbolic PDESystem and generates an OptimizationProblem for a neural network which represents the solution via a Physics-Informed Neural Network (PINN).
-
[D] Has anyone worked with Physics Informed Neural Networks (PINNs)?
NeuralPDE.jl fully automates the approach (and extensions of it, which are required to make it solve practical problems) from symbolic descriptions of PDEs, so that might be a good starting point to both learn the practical applications and get something running in a few minutes. As part of MIT 18.337 Parallel Computing and Scientific Machine Learning I gave an early lecture on physics-informed neural networks (with a two part video) describing the approach, how it works and what its challenges are. You might find those resources enlightening.
-
Doing Symbolic Math with SymPy
What is great about ModelingToolkit.jl is how its used in practical ways for other packages. E.g. NeuralPDE.jl.
Compared to SymPy, I feel that it is less of a "how do I integrate this function" package and more about "how can I build this DSL" framework.
https://github.com/SciML/NeuralPDE.jl
What are some alternatives?
DiffEqDevTools.jl - Benchmarking, testing, and development tools for differential equations and scientific machine learning (SciML)
deepxde - A library for scientific machine learning and physics-informed learning
DifferentialEquations.jl - Multi-language suite for high-performance solvers of differential equations and scientific machine learning (SciML) components. Ordinary differential equations (ODEs), stochastic differential equations (SDEs), delay differential equations (DDEs), differential-algebraic equations (DAEs), and more in Julia.
SymPy - A computer algebra system written in pure Python
QMUL - Repository of code and notes for the MSc. in Maths at Queen Mary University of London
ModelingToolkit.jl - An acausal modeling framework for automatically parallelized scientific machine learning (SciML) in Julia. A computer algebra system for integrated symbolics for physics-informed machine learning and automated transformations of differential equations
ReservoirComputing.jl - Reservoir computing utilities for scientific machine learning (SciML)
AMDGPU.jl - AMD GPU (ROCm) programming in Julia
18337 - 18.337 - Parallel Computing and Scientific Machine Learning
Gridap.jl - Grid-based approximation of partial differential equations in Julia
auto-07p - AUTO is a publicly available software for continuation and bifurcation problems in ordinary differential equations originally written in 1980 and widely used in the dynamical systems community.
Pyston - A faster and highly-compatible implementation of the Python programming language.