A Hybrid Approach Based on Particle Swarm Optimization for Echo State Network Initialization

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F15%3A86099058" target="_blank" >RIV/61989100:27240/15:86099058 - isvavai.cz</a>

Výsledek na webu

<a href="http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7379636" target="_blank" >http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7379636</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/SMC.2015.504" target="_blank" >10.1109/SMC.2015.504</a>

Jazyk výsledku

angličtina

Název v původním jazyce

A Hybrid Approach Based on Particle Swarm Optimization for Echo State Network Initialization

Popis výsledku v původním jazyce

Echo state networks (ESNs) fulfill considerable promises for topology fine-Tuning in supervised training. However the randomness of the setting of ESN weights initialization affects badly the learning performance. On the other side, Particle Swarm Optimization (PSO) has proven its efficiency as an optimization tool to puzzle out optimal solutions in complex space. In this work, we present an ESN architecture to which we associate a PSO algorithm to pre-Train the weights within the network layers. A random distribution of the weights matrices is firstly performed. Then, these weights are pre-Trained in order to fit the application requirements. Once optimized, they are re-injected into the ESN model which, in its turn, undergoes a training process followed by a test phase. A comparison between the network performances before and after optimization process is performed. Empirical results show a reduction of learning errors in the case of PSO use. (C) 2015 IEEE.

Název v anglickém jazyce

A Hybrid Approach Based on Particle Swarm Optimization for Echo State Network Initialization

Popis výsledku anglicky

Echo state networks (ESNs) fulfill considerable promises for topology fine-Tuning in supervised training. However the randomness of the setting of ESN weights initialization affects badly the learning performance. On the other side, Particle Swarm Optimization (PSO) has proven its efficiency as an optimization tool to puzzle out optimal solutions in complex space. In this work, we present an ESN architecture to which we associate a PSO algorithm to pre-Train the weights within the network layers. A random distribution of the weights matrices is firstly performed. Then, these weights are pre-Trained in order to fit the application requirements. Once optimized, they are re-injected into the ESN model which, in its turn, undergoes a training process followed by a test phase. A comparison between the network performances before and after optimization process is performed. Empirical results show a reduction of learning errors in the case of PSO use. (C) 2015 IEEE.

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2015

Kód důvěrnosti údajů

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

Název statě ve sborníku

2015 IEEE International Conference On Systems, Man And Cybernetics (Smc 2015) : Big Data Analytics For Human-Centric Systems

ISBN

978-1-4799-8696-5

ISSN

1062-922X

e-ISSN

—

Počet stran výsledku

6

Strana od-do

2896-2901

Název nakladatele

IEEE Computer Society

Místo vydání

Los Alamitos

Místo konání akce

Hong Kong

Datum konání akce

9. 10. 2015

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000368940202170