Empirical analysis of the necessary and sufficient conditions of the echo state property

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F17%3A00315146" target="_blank" >RIV/68407700:21230/17:00315146 - isvavai.cz</a>

Result on the web

<a href="http://ieeexplore.ieee.org/document/7965946/" target="_blank" >http://ieeexplore.ieee.org/document/7965946/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/IJCNN.2017.7965946" target="_blank" >10.1109/IJCNN.2017.7965946</a>

Result language

angličtina

Original language name

Empirical analysis of the necessary and sufficient conditions of the echo state property

Original language description

The Echo State Network (ESN) is a specific recurrent network, which has gained popularity during the last years. The model has a recurrent network named reservoir, that is fixed during the learning process. The reservoir is used for transforming the input space in a larger space. A fundamental property that provokes an impact on the model accuracy is the Echo State Property (ESP). There are two main theoretical results related to the ESP. First, a sufficient condition for the ESP existence that involves the singular values of the reservoir matrix. Second, a necessary condition for the ESP. The ESP can be violated according to the spectral radius value of the reservoir matrix. There is a theoretical gap between these necessary and sufficient conditions. This article presents an empirical analysis of the accuracy and the projections of reservoirs that satisfy this theoretical gap. It gives some insights about the generation of the reservoir matrix. From previous works, it is already known that the optimal accuracy is obtained near to the border of stability control of the dynamics. Then, according to our empirical results, we can see that this border seems to be closer to the sufficient conditions than to the necessary conditions of the ESP.

Czech name

—

Czech description

—

Type

D - Article in proceedings

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

Article name in the collection

Proceedings of the International Joint Conference on Neural Networks

ISBN

978-1-5090-6181-5

ISSN

—

e-ISSN

—

Number of pages

9

Pages from-to

888-896

Publisher name

IEEE Xplore

Place of publication

—

Event location

Anchorage

Event date

May 14, 2017

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—