Dynamical time series embeddings in recurrent neural networks

Gonzalo Uribarri and Gabriel B. Mindlin

Chaos, Solitons & Fractals, 2022, vol. 154, issue C

Abstract: Time series forecasting has historically been a key research problem in science and engineering. In recent years, machine learning algorithms have proven to be a very successful data-driven approach in this area. In particular, Recurrent Neural Networks (RNNs) represent the state-of-the-art algorithms in many sequential tasks. In this paper we train Long Short Term Memory networks (LSTM), which are a type of RNNs, to make predictions in time series corresponding to the observation of a single variable of a chaotic system. We show that, under certain conditions, networks learn to generate an embedding of the data in their inner sate that is topologically equivalent to the original strange attractor. Remarkably, this resembles standard forecasting methods from nonlinear science in which the time series is embedded in a multi-valued space using Takens's delay embedding mechanism.

Keywords: Recurrent neural networks; Time series; Dynamical systems; Embedding; Forecasting (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (5)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0960077921009668
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:chsofr:v:154:y:2022:i:c:s0960077921009668

DOI: 10.1016/j.chaos.2021.111612

Access Statistics for this article

Chaos, Solitons & Fractals is currently edited by Stefano Boccaletti and Stelios Bekiros

More articles in Chaos, Solitons & Fractals from Elsevier
Bibliographic data for series maintained by Thayer, Thomas R. ().