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

12/30/2018
by   Claudio Gallicchio, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/17/2022

Recurrent Neural Networks for Forecasting Time Series with Multiple Seasonality: A Comparative Study

This paper compares recurrent neural networks (RNNs) with different type...
research
01/29/2019

Short-term Demand Forecasting for Online Car-hailing Services using Recurrent Neural Networks

Short-term traffic flow prediction is one of the crucial issues in intel...
research
03/29/2018

Modeling the spatio-temporal dynamics of land use change with recurrent neural networks

This study applies recurrent neural networks (RNNs), which are known for...
research
10/29/2021

Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains

A common approach to prediction and planning in partially observable dom...
research
05/10/2019

Large-Scale Spectrum Occupancy Learning via Tensor Decomposition and LSTM Networks

A new paradigm for large-scale spectrum occupancy learning based on long...
research
06/21/2018

Gated Complex Recurrent Neural Networks

Complex numbers have long been favoured for digital signal processing, y...

Please sign up or login with your details

Forgot password? Click here to reset