Corpus ID: 211989200

Forecasting Sequential Data using Consistent Koopman Autoencoders

@article{Azencot2020ForecastingSD,
  title={Forecasting Sequential Data using Consistent Koopman Autoencoders},
  author={Omri Azencot and N. Benjamin Erichson and Vanessa F.C. Lin and Michael W. Mahoney},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.02236}
}
  • Omri Azencot, N. Benjamin Erichson, +1 author Michael W. Mahoney
  • Published 2020
  • Computer Science, Physics, Mathematics
  • ArXiv
  • Recurrent neural networks are widely used on time series data, yet such models often ignore the underlying physical structures in such sequences. A new class of physically-based methods related to Koopman theory has been introduced, offering an alternative for processing nonlinear dynamical systems. In this work, we propose a novel Consistent Koopman Autoencoder model which, unlike the majority of existing work, leverages the forward and backward dynamics. Key to our approach is a new analysis… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-4 OF 4 CITATIONS

    Lipschitz Recurrent Neural Networks

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Mode Decomposition for Homogeneous Symmetric Operators

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Noise-response Analysis for Rapid Detection of Backdoors in Deep Neural Networks

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 44 REFERENCES

    Deep learning for universal linear embeddings of nonlinear dynamics

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Hamiltonian Neural Networks

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Bidirectional recurrent neural networks

    VIEW 13 EXCERPTS
    HIGHLY INFLUENTIAL

    Hamiltonian Systems and Transformation in Hilbert Space.

    • Bernard O. Koopman
    • Medicine, Mathematics, Computer Science
    • Proceedings of the National Academy of Sciences of the United States of America
    • 1931
    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Neural Ordinary Differential Equations

    VIEW 13 EXCERPTS
    HIGHLY INFLUENTIAL

    Supervised Sequence Labelling

    VIEW 13 EXCERPTS
    HIGHLY INFLUENTIAL

    Symplectic Recurrent Neural Networks

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL