A Hybrid Approach Based on Particle Swarm Optimization for Echo State Network Initialization
The result's identifiers
Result code in 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>
Result on the web
<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>
Alternative languages
Result language
angličtina
Original language name
A Hybrid Approach Based on Particle Swarm Optimization for Echo State Network Initialization
Original language description
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.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
IN - Informatics
OECD FORD branch
—
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2015
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
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
—
Number of pages
6
Pages from-to
2896-2901
Publisher name
IEEE Computer Society
Place of publication
Los Alamitos
Event location
Hong Kong
Event date
Oct 9, 2015
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000368940202170