Experimental analysis of a hybrid reservoir computing technique

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F16%3A86099078" target="_blank" >RIV/61989100:27240/16:86099078 - isvavai.cz</a>
Result on the web
<a href="https://link.springer.com/chapter/10.1007/978-3-319-27221-4_20" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-319-27221-4_20</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-319-27221-4_20" target="_blank" >10.1007/978-3-319-27221-4_20</a>

Result language
angličtina
Original language name
Experimental analysis of a hybrid reservoir computing technique
Original language description
Recently a new Neural Network model named Reservoir with Random Static Projections (R2SP) was introduced in the literature. The method belongs to the popular family of Reservoir Computing (RC) models. The R2SP method is a combination of the RC models and Extreme Learning Machines (ELMs). In this article, we analyse the accuracy of a variation of the R2SP that consists of using Radial Basis Functions (RBF) projections instead of ELMs. We evaluate the proposed variation on two simulated benchmark problems obtaining promising results with respect to other RC models. (C) Springer International Publishing Switzerland 2016.
Czech name
—
Czech description
—

Publication year
2016
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Advances in Intelligent Systems and Computing. Volume 420
ISBN
978-3-319-27220-7
ISSN
2194-5357
e-ISSN
—
Number of pages
11
Pages from-to
237-247
Publisher name
Springer Verlag
Place of publication
London
Event location
Soul
Event date
Nov 16, 2015
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)