elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Reliable and Fast Recurrent Neural Network Architecture Optimization

Camero, Andrés and Toutouh, Jamal and Alba, Enrique (2021) Reliable and Fast Recurrent Neural Network Architecture Optimization. In: Proceedings of the XIX Conference of the Spanish Association for Artificial Intelligence, pp. 219-220. XIX Conference of the Spanish Association for Artificial Intelligence, 2021-09-22 - 2021-09-24, Malaga, Spain. ISBN 978-84-09-30514-8.

[img] PDF
181kB

Official URL: https://caepia20-21.uma.es/proceedings.html

Abstract

This article introduces Random Error Sampling-based Neuroevolution (RESN), a novel automatic method to optimize recurrent neural network architectures. RESN combines an evolutionary algorithm with a training-free evaluation approach. The results show that RESN achieves state-of-the-art error performance while reducing by half the computational time.

Item URL in elib:https://elib.dlr.de/188382/
Document Type:Conference or Workshop Item (Speech)
Title:Reliable and Fast Recurrent Neural Network Architecture Optimization
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Camero, AndrésUNSPECIFIEDhttps://orcid.org/0000-0002-8152-9381UNSPECIFIED
Toutouh, JamalUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Alba, EnriqueUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Date:22 September 2021
Journal or Publication Title:Proceedings of the XIX Conference of the Spanish Association for Artificial Intelligence
Refereed publication:No
Open Access:Yes
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Page Range:pp. 219-220
ISBN:978-84-09-30514-8
Status:Published
Keywords:neuroevolution, evolutionary algorithms, metaheuristics, recurrent neural networks
Event Title:XIX Conference of the Spanish Association for Artificial Intelligence
Event Location:Malaga, Spain
Event Type:international Conference
Event Start Date:22 September 2021
Event End Date:24 September 2021
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Earth Observation
DLR - Research theme (Project):R - Artificial Intelligence
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > EO Data Science
Deposited By: Camero, Dr Andres
Deposited On:27 Sep 2022 13:32
Last Modified:24 Apr 2024 20:49

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.