A fast noise filtering algorithm for time series prediction using recurrent neural networks
Machine Learning
2020-10-07 v3 Dynamical Systems
Machine Learning
Abstract
Recent research demonstrate that prediction of time series by recurrent neural networks (RNNs) based on the noisy input generates a smooth anticipated trajectory. We examine the internal dynamics of RNNs and establish a set of conditions required for such behavior. Based on this analysis we propose a new approximate algorithm and show that it significantly speeds up the predictive process without loss of accuracy.
Cite
@article{arxiv.2007.08063,
title = {A fast noise filtering algorithm for time series prediction using recurrent neural networks},
author = {Boris Rubinstein},
journal= {arXiv preprint arXiv:2007.08063},
year = {2020}
}
Comments
15 pages, 10 figures; typos corrected; the notation table removed; an appendix added