LOCALLY CONNECTED ECHO STATE NETWORKS FOR TIME SERIES FORECASTING

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A10513155" target="_blank" >RIV/00216208:11320/25:10513155 - isvavai.cz</a>

Result on the web

<a href="https://openreview.net/attachment?id=KeRwLLwZaw&name=pdf" target="_blank" >https://openreview.net/attachment?id=KeRwLLwZaw&name=pdf</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

LOCALLY CONNECTED ECHO STATE NETWORKS FOR TIME SERIES FORECASTING

Original language description

Echo State Networks (ESNs) are a class of recurrent neural networks in which only a small readout regression layer is trained, while the weights of the recurrent network, termed the reservoir, are randomly assigned and remain fixed. Our work introduces the Locally Connected ESN (LCESN), a novel ESN variant with a locally connected reservoir, forced memory, and a weight adaptation strategy. LCESN significantly reduces the asymptotic time and space complexities compared to the conventional ESN, enabling substantially larger networks. LCESN also improves the memory properties of ESNs without affecting network stability. We evaluate LCESN&apos;s performance on the NARMA10 benchmark task and compare it to state-of-the-art models on nine real-world datasets. Despite the simplicity of our model and its one-shot training approach, LCESN achieves competitive results, even surpassing several state-of-the-art models. LCESN introduces a fresh approach to real-world time series forecasting and demonstrates that large, well-tuned random recurrent networks can rival complex gradient-trained feedforward models. We provide our GPU-based implementation of LCESN as an open-source library.

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<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2025

Confidentiality

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

Article name in the collection

13th International Conference on Learning Representations, ICLR 2025

ISBN

979-8-3313-2085-0

ISSN

—

e-ISSN

—

Number of pages

22

Pages from-to

51172-51193

Publisher name

International Conference on Learning Representations, ICLR

Place of publication

Neuveden

Event location

Singapore

Event date

Apr 24, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—