Evolutionary Echo State Network: A neuroevolutionary framework for time series prediction

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F23%3A10253424" target="_blank" >RIV/61989100:27240/23:10253424 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S1568494623004817?via%3Dihub" target="_blank" >https://www.sciencedirect.com/science/article/pii/S1568494623004817?via%3Dihub</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.asoc.2023.110463" target="_blank" >10.1016/j.asoc.2023.110463</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Evolutionary Echo State Network: A neuroevolutionary framework for time series prediction

Popis výsledku v původním jazyce

From one side, Evolutionary Algorithms have enabled enormous progress over the last years in the optimization field. They have been applied to a variety of problems, including optimization of Neural Networks&apos; architectures. On the other side, the Echo State Network (ESN) model has become increasingly popular in time series prediction, for instance when modeling chaotic sequences. The network has numerous hidden neurons forming a recurrent topology, so-called reservoir, which is fixed during the learning process. Initial reservoir design has mostly been made by human experts; as a consequence, it is prone to errors and bias, and it is a time consuming task. In this paper, we introduce an automatic general neuroevolutionary framework for ESNs, on which we develop a computational tool for evolving reservoirs, called EVOlutionary Echo State Network (EvoESN). To increase efficiency, we represent the large matrix of reservoir weights in the Fourier space, where we perform the evolutionary search strategy. This frequency space has major advantages compared with the original weight space. After updating the Fourier coefficients, we go back to the weight space and perform a conventional training phase for full setting the reservoir architecture. We analyze the evolutionary search employing genetic algorithms and particle swarm optimization, obtaining promising results with the latter over three well-known chaotic time series. The proposed framework leads fast to very good results compared with modern ESN models. Hence, this contribution positions an important family of recurrent systems in the promising neuroevolutionary domain.&amp; COPY; 2023 Elsevier B.V. All rights reserved.

Název v anglickém jazyce

Evolutionary Echo State Network: A neuroevolutionary framework for time series prediction

Popis výsledku anglicky

From one side, Evolutionary Algorithms have enabled enormous progress over the last years in the optimization field. They have been applied to a variety of problems, including optimization of Neural Networks&apos; architectures. On the other side, the Echo State Network (ESN) model has become increasingly popular in time series prediction, for instance when modeling chaotic sequences. The network has numerous hidden neurons forming a recurrent topology, so-called reservoir, which is fixed during the learning process. Initial reservoir design has mostly been made by human experts; as a consequence, it is prone to errors and bias, and it is a time consuming task. In this paper, we introduce an automatic general neuroevolutionary framework for ESNs, on which we develop a computational tool for evolving reservoirs, called EVOlutionary Echo State Network (EvoESN). To increase efficiency, we represent the large matrix of reservoir weights in the Fourier space, where we perform the evolutionary search strategy. This frequency space has major advantages compared with the original weight space. After updating the Fourier coefficients, we go back to the weight space and perform a conventional training phase for full setting the reservoir architecture. We analyze the evolutionary search employing genetic algorithms and particle swarm optimization, obtaining promising results with the latter over three well-known chaotic time series. The proposed framework leads fast to very good results compared with modern ESN models. Hence, this contribution positions an important family of recurrent systems in the promising neuroevolutionary domain.&amp; COPY; 2023 Elsevier B.V. All rights reserved.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GF21-33574K" target="_blank" >GF21-33574K: Celoživotní strojové učení z datových proudů</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Applied Soft Computing

ISSN

1568-4946

e-ISSN

1872-9681

Svazek periodika

144

Číslo periodika v rámci svazku

September

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

14

Strana od-do

—

Kód UT WoS článku

001054625900001

EID výsledku v databázi Scopus

2-s2.0-85162172245