DiffEqFlux.jl logo
DiffEqFlux.jl
  • DiffEqFlux.jl: Generalized Physics-Informed and Scientific Machine Learning (SciML)
  • Basic Parameter Fitting Tutorials
    • Optimization of Ordinary Differential Equations
    • Optimization of Stochastic Differential Equations
    • Lotka-Volterra with Flux.train!
    • Delay Differential Equations
    • Partial Differential Equation Constrained Optimization
    • Parameter Estimation on Highly Stiff Systems
  • Neural ODE and SDE Tutorials
    • Neural Ordinary Differential Equations with sciml_train
    • Neural Ordinary Differential Equations with Flux.train!
    • GPU-based MNIST Neural ODE Classifier
    • Neural Stochastic Differential Equations
    • Augmented Neural Ordinary Differential Equations
    • Smoothed Collocation for Fast Two-Stage Training
    • Neural Graph Differential Equations
    • Continuous Normalizing Flows with sciml_train
  • Bayesian Estimation Tutorials
    • Bayesian Estimation of Differential Equations with Probabilistic Programming
    • Bayesian Neural ODEs: NUTS
    • Bayesian Neural ODEs: SGLD
  • FAQ, Tips, and Tricks
    • Strategies to Avoid Local Minima
    • Simultaneous Fitting of Multiple Neural Networks
    • Data-Parallel Multithreaded, Distributed, and Multi-GPU Batching
    • Neural Second Order Ordinary Differential Equation
    • Newton and Hessian-Free Newton-Krylov with Second Order Adjoint Sensitivity Analysis
    • Training a Neural Ordinary Differential Equation with Mini-Batching
  • Hybrid and Jump Tutorials
    • Training Neural Networks in Hybrid Differential Equations
    • Bouncing Ball Hybrid ODE Optimization
    • Neural Jump Diffusions (Neural Jump SDE) and Neural Partial Differential Equations (Neural PDEs)
  • Optimal and Model Predictive Control Tutorials
    • Solving Optimal Control Problems with Universal Differential Equations
    • Universal Differential Equations for Neural Feedback Control
  • Universal Differential Equations and Physical Constraints Tutorials
    • Universal Ordinary, Stochastic, and Partial Diffrential Equation Examples
    • Handling Exogenous Input Signals
    • Enforcing Physical Constraints via Universal Differential-Algebraic Equations
    • Physics Informed Machine Learning with TensorLayer
    • Hamiltonian Neural Network
  • Layer APIs
    • Classical Basis Layers
    • Tensor Product Layer
    • Continuous Normalizing Flows Layer
    • Spline Layer
    • Neural Differential Equation Layers
    • Hamiltonian Neural Network Layer
  • Manual and APIs
    • Controlling Choices of Adjoints
    • Use with Flux Chain and train!
    • FastChain
    • Smoothed Collocation
    • GPUs
    • sciml_train
  • Benchmarks
Version
  • Hybrid and Jump Tutorials
  • Neural Jump Diffusions (Neural Jump SDE) and Neural Partial Differential Equations (Neural PDEs)
  • Neural Jump Diffusions (Neural Jump SDE) and Neural Partial Differential Equations (Neural PDEs)
Edit on GitHub

Neural Jump Diffusions (Neural Jump SDE) and Neural Partial Differential Equations (Neural PDEs)

For the sake of not having a never-ending documentation of every single combination of CPU/GPU with every layer and every neural differential equation, we will end here. But you may want to consult this blog post which showcases defining neural jump diffusions and neural partial differential equations.

« Bouncing Ball Hybrid ODE OptimizationSolving Optimal Control Problems with Universal Differential Equations »

Settings


This document was generated with Documenter.jl on Wednesday 20 January 2021. Using Julia version 1.4.2.