Corpus ID: 49310446

Neural Ordinary Differential Equations

@inproceedings{Chen2018NeuralOD,
  title={Neural Ordinary Differential Equations},
  author={Tian Qi Chen and Yulia Rubanova and J. Bettencourt and D. Duvenaud},
  booktitle={NeurIPS},
  year={2018}
}
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
Differential equations as models of deep neural networks
Piecewise-constant Neural ODEs
Neural Stochastic Differential Equations
Port–Hamiltonian Approach to Neural Network Training
Differential Bayesian Neural Nets
Neural Optimal Control for Representation Learning
Generative Modeling with Neural Ordinary Differential Equations
Time Dependence in Non-Autonomous Neural ODEs
Deterministic Inference of Neural Stochastic Differential Equations
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 67 REFERENCES
PDE-Net: Learning PDEs from Data
Black-Box Variational Inference for Stochastic Differential Equations
Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
  • M. Raissi
  • Mathematics, Computer Science
  • J. Mach. Learn. Res.
  • 2018
Stochastic Backpropagation and Approximate Inference in Deep Generative Models
Gradient calculations for dynamic recurrent neural networks: a survey
Hidden physics models: Machine learning of nonlinear partial differential equations
Reversible Architectures for Arbitrarily Deep Residual Neural Networks
Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations
OptNet: Differentiable Optimization as a Layer in Neural Networks
Variable Computation in Recurrent Neural Networks
...
1
2
3
4
5
...