Time-Adaptive Recurrent Neural Networks

no code implementations • 11 Apr 2022 • Mantas Lukoševičius, Arnas Uselis

We propose an elegant alternative approach where instead the RNN is in effect resampled in time to match the time of the data.

Efficient implementations of echo state network cross-validation

1 code implementation • 19 Jun 2020 • Mantas Lukoševičius, Arnas Uselis

The second level of optimization also makes the (ii) part remain constant irrespective of large $k$, as long as the dimension of the output is low.

One-Shot Learning Time Series

Localized convolutional neural networks for geospatial wind forecasting

1 code implementation • 12 May 2020 • Arnas Uselis, Mantas Lukoševičius, Lukas Stasytis

They can be added to any convolutional layers, easily end-to-end trained, introduce minimal additional complexity, and let CNNs retain most of their benefits to the extent that they are needed.

Translation

Efficient Cross-Validation of Echo State Networks

1 code implementation • 22 Aug 2019 • Mantas Lukoševičius, Arnas Uselis

Thus in many situations $k$-fold cross-validation of ESNs can be done for virtually the same time complexity as a simple single split validation.

One-Shot Learning Time Series