Corpus ID: 1520978

Autoregressive Convolutional Neural Networks for Asynchronous Time Series

@article{Binkowski2018AutoregressiveCN,
  title={Autoregressive Convolutional Neural Networks for Asynchronous Time Series},
  author={Mikolaj Binkowski and Gautier Marti and Philippe Donnat},
  journal={ArXiv},
  year={2018},
  volume={abs/1703.04122}
}
  • Mikolaj Binkowski, Gautier Marti, Philippe Donnat
  • Published 2018
  • Computer Science, Mathematics
  • ArXiv
  • We propose Significance-Offset Convolutional Neural Network, a deep convolutional network architecture for regression of multivariate asynchronous time series. The model is inspired by standard autoregressive (AR) models and gating mechanisms used in recurrent neural networks. It involves an AR-like weighting system, where the final predictor is obtained as a weighted sum of adjusted regressors, while the weights are datadependent functions learnt through a convolutional network. The… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 36 CITATIONS

    Convolutional Neural Networks for Energy Time Series Forecasting

    VIEW 4 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    A Novel LSTM Approach for Asynchronous Multivariate Time Series Prediction

    • King Ma, Henry Leung
    • Computer Science
    • 2019 International Joint Conference on Neural Networks (IJCNN)
    • 2019

    Predict Forex Trend via Convolutional Neural Networks

    VIEW 11 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    FILTER CITATIONS BY YEAR

    2017
    2020

    CITATION STATISTICS

    • 4 Highly Influenced Citations

    • Averaged 12 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 60 REFERENCES