Neural Ordinary Differential Equations
GPTKB entity
Statements (32)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:model
|
| gptkbp:abbreviation |
Neural ODEs
|
| gptkbp:application |
latent variable models
continuous normalizing flows time series modeling |
| gptkbp:citation |
over 5000 (as of 2024)
|
| gptkbp:field |
gptkb:machine_learning
deep learning partial differential equations |
| gptkbp:hasConcept |
parameterize the derivative of hidden state using a neural network
|
| https://www.w3.org/2000/01/rdf-schema#label |
Neural Ordinary Differential Equations
|
| gptkbp:impact |
inspired research in continuous-time deep learning
|
| gptkbp:introduced |
Ricky T. Q. Chen
|
| gptkbp:introducedIn |
2018
|
| gptkbp:mainPaperAuthors |
gptkb:David_Duvenaud
Jesse Bettencourt Ricky T. Q. Chen Yulia Rubanova |
| gptkbp:mainPaperTitle |
gptkb:Neural_Ordinary_Differential_Equations
|
| gptkbp:mainPaperURL |
https://arxiv.org/abs/1806.07366
|
| gptkbp:mainPaperYear |
2018
|
| gptkbp:openSource |
DiffEqFlux.jl
torchdiffeq |
| gptkbp:publishedIn |
gptkb:NeurIPS_2018
|
| gptkbp:relatedTo |
ODE solvers
residual networks continuous-depth models |
| gptkbp:trainer |
adjoint sensitivity method
|
| gptkbp:usedIn |
modeling dynamical systems
physics-informed machine learning |
| gptkbp:bfsParent |
gptkb:Google_Brain_(former)
|
| gptkbp:bfsLayer |
7
|