Echo State Queueing Networks: A Combination of Reservoir Computing and Random Neural Networks

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F17%3A00311786" target="_blank" >RIV/68407700:21230/17:00311786 - isvavai.cz</a>

Result on the web

<a href="https://www.cambridge.org/core/journals/probability-in-the-engineering-and-informational-sciences/article/echo-state-queueing-networks-a-combination-of-reservoir-computing-and-random-neural-networks/B61D5741A5AD03BC3B6433BA139940D4" target="_blank" >https://www.cambridge.org/core/journals/probability-in-the-engineering-and-informational-sciences/article/echo-state-queueing-networks-a-combination-of-reservoir-computing-and-random-neural-networks/B61D5741A5AD03BC3B6433BA139940D4</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1017/S0269964817000110" target="_blank" >10.1017/S0269964817000110</a>

Result language

angličtina

Original language name

Echo State Queueing Networks: A Combination of Reservoir Computing and Random Neural Networks

Original language description

This paper deals with two ideas appeared during the last developing phase in Artificial Intelligence: Reservoir Computing (RC) and Random Neural Networks. Both have been very successful in many applications. We propose a new model belonging to the first class, taking the structure of the second for its dynamics. The new model is called Echo State Queuing Network. The paper positions the model in the global Machine Learning area, and provides examples of its use and performances. We show on largely used benchmarks that it is a very accurate tool, and we illustrate how it compares with standard RC models.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

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

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2017

Confidentiality

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

Name of the periodical

Probability in the Engineering and Informational Sciences

ISSN

0269-9648

e-ISSN

1469-8951

Volume of the periodical

31

Issue of the periodical within the volume

4

Country of publishing house

GB - UNITED KINGDOM

Number of pages

20

Pages from-to

457-476

UT code for WoS article

000411729100006

EID of the result in the Scopus database

2-s2.0-85019205684