Efficient Cross-Validation of Echo State Networks

@article{Lukosevicius2019EfficientCO,
  title={Efficient Cross-Validation of Echo State Networks},
  author={Mantas Lukosevicius and Arnas Uselis},
  journal={ArXiv},
  year={2019},
  volume={abs/1908.08450}
}
  • Mantas Lukosevicius, Arnas Uselis
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • Echo State Networks (ESNs) are known for their fast and precise one-shot learning of time series. But they often need good hyper-parameter tuning for best performance. For this good validation is key, but usually, a single validation split is used. In this rather practical contribution we suggest several schemes for cross-validating ESNs and introduce an efficient algorithm for implementing them. The component that dominates the time complexity of the already quite fast ESN training remains… CONTINUE READING
    2 Citations

    Figures, Tables, and Topics from this paper.

    Efficient implementations of echo state network cross-validation

    References

    SHOWING 1-10 OF 11 REFERENCES
    Re-visiting the echo state property
    • 207
    • PDF
    A note on the validity of cross-validation for evaluating autoregressive time series prediction
    • 131
    • PDF
    Optimization and applications of echo state networks with leaky- integrator neurons
    • 532
    • PDF
    A Practical Guide to Applying Echo State Networks
    • 360
    • PDF
    Reservoir computing approaches to recurrent neural network training
    • 1,336
    • PDF
    Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication
    • 2,029
    • PDF
    The''echo state''approach to analysing and training recurrent neural networks
    • 1,532
    • PDF
    Short-term electricity demand forecasting using double seasonal exponential smoothing
    • J. Taylor
    • Computer Science
    • J. Oper. Res. Soc.
    • 2003
    • 506
    • PDF
    Cross‐Validatory Choice and Assessment of Statistical Predictions
    • 6,196
    Echo state network
    • H. Jaeger
    • Computer Science, Physics
    • Scholarpedia
    • 2007
    • 197