Corpus ID: 49310446

Neural Ordinary Differential Equations

@article{Chen2018NeuralOD,
  title={Neural Ordinary Differential Equations},
  author={Tian Qi Chen and Yulia Rubanova and Jesse Bettencourt and David Kristjanson Duvenaud},
  journal={ArXiv},
  year={2018},
  volume={abs/1806.07366}
}
  • Tian Qi Chen, Yulia Rubanova, +1 author David Kristjanson Duvenaud
  • Published 2018
  • Computer Science, Mathematics
  • ArXiv
  • We introduce a new family of deep neural network models. [...] Key Method We also construct continuous normalizing flows, a generative model that can train by maximum likelihood, without partitioning or ordering the data dimensions. For training, we show how to scalably backpropagate through any ODE solver, without access to its internal operations. This allows end-to-end training of ODEs within larger models.Expand Abstract

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 528 CITATIONS

    Differential equations as models of deep neural networks

    VIEW 4 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Differential Bayesian Neural Nets

    VIEW 2 EXCERPTS
    CITES BACKGROUND & METHODS

    Port–Hamiltonian Approach to Neural Network Training

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Generative Modeling with Neural Ordinary Differential Equations

    VIEW 14 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Time Dependence in Non-Autonomous Neural ODEs

    VIEW 6 EXCERPTS
    HIGHLY INFLUENCED

    NeuPDE: Neural Network Based Ordinary and Partial Differential Equations for Modeling Time-Dependent Data

    VIEW 9 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    FILTER CITATIONS BY YEAR

    2018
    2020

    CITATION STATISTICS

    • 130 Highly Influenced Citations

    • Averaged 175 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 67 REFERENCES

    PDE-Net: Learning PDEs from Data

    VIEW 2 EXCERPTS

    Stable Architectures for Deep Neural Networks

    VIEW 2 EXCERPTS

    Variable Computation in Recurrent Neural Networks

    VIEW 1 EXCERPT