Hyperparameter Tuning in Echo State Networks

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3A10455492" target="_blank" >RIV/00216208:11320/22:10455492 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.1145/3512290.3528721" target="_blank" >https://doi.org/10.1145/3512290.3528721</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3512290.3528721" target="_blank" >10.1145/3512290.3528721</a>

Result language

angličtina

Original language name

Hyperparameter Tuning in Echo State Networks

Original language description

Echo State Networks represent a type of recurrent neural network with a large randomly generated reservoir and a small number of readout connections trained via linear regression. The most common topology of the reservoir is a fully connected network of up to thousands of neurons. Over the years, researchers have introduced a variety of alternative reservoir topologies, such as a circular network or a linear path of connections. When comparing the performance of different topologies or other architectural changes, it is necessary to tune the hyperparameters for each of the topologies separately since their properties may significantly differ. The hyperparameter tuning is usually carried out manually by selecting the best performing set of parameters from a sparse grid of predefined combinations. Unfortunately, this approach may lead to underperforming configurations, especially for sensitive topologies. We propose an alternative approach of hyperparameter tuning based on the Covariance Matrix Adaptation Evolution Strategy (CMA-ES). Using this approach, we have improved multiple topology comparison results by orders of magnitude suggesting that topology alone does not play as important role as properly tuned hyperparameters.

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

S - Specificky vyzkum na vysokych skolach

Publication year

2022

Confidentiality

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

Article name in the collection

GECCO &apos;22: Proceedings of the Genetic and Evolutionary Computation Conference

ISBN

978-1-4503-9237-2

ISSN

—

e-ISSN

—

Number of pages

9

Pages from-to

404-412

Publisher name

Association for Computing Machinery

Place of publication

New York

Event location

Boston

Event date

Jul 9, 2022

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

000847380200048