DiffEqFlux.jl – A Julia Library for Neural Differential Equations

DiffEqFlux.jl – A Julia Library for Neural Differential Equations...

DiffEqFlux.jl – A Julia Library for Neural Differential Equations DiffEqFlux.jl – A Julia Library for Neural Differential Equations 18 January 2019 | Chris Rackauckas, Mike Innes, Yingbo Ma, Jesse Bettencourt, Lyndon White, Vaibhav Dixit Translations: Traditional Chinese In this blog post we will show you how to easily, efficiently, and robustly use differential equation (DiffEq) solvers with neural networks in Julia. The Neural Ordinary Differential Equations paper has attracted significant attention even before it was awarded one of the Best Papers of NeurIPS 2018. The paper already

related reading

• 1806.07366arxiv.org
• GitHub - DiffEqML/torchdyn: A PyTorch library entirely dedicated to neural differential equations, implicit models and related numerical methodsgithub.com
• Neural Ordinary Differential Equationsarxiv.org
• Neural Manifold Ordinary Differential Equationsarxiv.org
• Stochastic Differential Equations, Deep Learning, and High-Dimensional PDEsmitmath.github.io
• Differentiable Programming from Scratchthenumb.at
• Learning the integral of a diffusion model – Sander Dielemansander.ai
• Hamiltonian Neural PDE Solvers through Functional Approximationarxiv.org
• What nonlinear solvers are available? - Specific Domains - Julia Programming Languagediscourse.julialang.org
• [1907.03452] Deep splitting method for parabolic PDEsarxiv.org
• Deep Learning for Symbolic Mathematicsarxiv.org
• proceedings.mlr.press/v202/ma23a/ma23a.pdfproceedings.mlr.press