Comparison between DeepESNs and gated RNNs on multivariate time-series prediction

Autor:	Gallicchio, Claudio, Micheli, Alessio, Pedrelli, Luca
Rok vydání:	2018
Předmět:	Computer Science - Machine Learning Computer Science - Neural and Evolutionary Computing Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	We propose an experimental comparison between Deep Echo State Networks (DeepESNs) and gated Recurrent Neural Networks (RNNs) on multivariate time-series prediction tasks. In particular, we compare reservoir and fully-trained RNNs able to represent signals featured by multiple time-scales dynamics. The analysis is performed in terms of efficiency and prediction accuracy on 4 polyphonic music tasks. Our results show that DeepESN is able to outperform ESN in terms of prediction accuracy and efficiency. Whereas, between fully-trained approaches, Gated Recurrent Units (GRU) outperforms Long Short-Term Memory (LSTM) and simple RNN models in most cases. Overall, DeepESN turned out to be extremely more efficient than others RNN approaches and the best solution in terms of prediction accuracy on 3 out of 4 tasks. Comment: Preprint version of Claudio Gallicchio, Alessio Micheli and Luca Pedrelli (2019) Comparison between DeepESNs and gated RNNs on multivariate time-series prediction. In: ESANN 2019 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium), 24-26 April 2019, i6doc.com publ., ISBN 978-287-587-065-0
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1812.11527 Zobrazit plný text záznamu View this record from Arxiv