no code implementations • 11 May 2024 • Peter Tino, Robert Simon Fong, Roberto Fabio Leonarduzzi
Rather surprisingly we show that even when linear readout is employed, our method has the capacity to outperform transformer models on univariate time series and attain competitive results on multivariate benchmark datasets.
no code implementations • 21 Aug 2023 • Boyu Li, Robert Simon Fong, Peter Tiňo
Reservoir computation models form a subclass of recurrent neural networks with fixed non-trainable input and dynamic coupling weights.