paper

A fast noise filtering algorithm for time series prediction using recurrent neural networks

arXiv:2007.08063

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.

15 pages, 10 figures; typos corrected; the notation table removed; an appendix added

References in corpus (1)

Cited by in corpus (1)

A fast noise filtering algorithm for time series prediction using recurrent neural networks · wovepaper