Camero, Andrés und Toutouh, Jamal und Alba, Enrique (2021) Reliable and Fast Recurrent Neural Network Architecture Optimization. In: Proceedings of the XIX Conference of the Spanish Association for Artificial Intelligence, Seiten 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.
PDF
181kB |
Offizielle URL: https://caepia20-21.uma.es/proceedings.html
Kurzfassung
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.
elib-URL des Eintrags: | https://elib.dlr.de/188382/ | ||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dokumentart: | Konferenzbeitrag (Vortrag) | ||||||||||||||||
Titel: | Reliable and Fast Recurrent Neural Network Architecture Optimization | ||||||||||||||||
Autoren: |
| ||||||||||||||||
Datum: | 22 September 2021 | ||||||||||||||||
Erschienen in: | Proceedings of the XIX Conference of the Spanish Association for Artificial Intelligence | ||||||||||||||||
Referierte Publikation: | Nein | ||||||||||||||||
Open Access: | Ja | ||||||||||||||||
Gold Open Access: | Nein | ||||||||||||||||
In SCOPUS: | Nein | ||||||||||||||||
In ISI Web of Science: | Nein | ||||||||||||||||
Seitenbereich: | Seiten 219-220 | ||||||||||||||||
ISBN: | 978-84-09-30514-8 | ||||||||||||||||
Status: | veröffentlicht | ||||||||||||||||
Stichwörter: | neuroevolution, evolutionary algorithms, metaheuristics, recurrent neural networks | ||||||||||||||||
Veranstaltungstitel: | XIX Conference of the Spanish Association for Artificial Intelligence | ||||||||||||||||
Veranstaltungsort: | Malaga, Spain | ||||||||||||||||
Veranstaltungsart: | internationale Konferenz | ||||||||||||||||
Veranstaltungsbeginn: | 22 September 2021 | ||||||||||||||||
Veranstaltungsende: | 24 September 2021 | ||||||||||||||||
HGF - Forschungsbereich: | Luftfahrt, Raumfahrt und Verkehr | ||||||||||||||||
HGF - Programm: | Raumfahrt | ||||||||||||||||
HGF - Programmthema: | Erdbeobachtung | ||||||||||||||||
DLR - Schwerpunkt: | Raumfahrt | ||||||||||||||||
DLR - Forschungsgebiet: | R EO - Erdbeobachtung | ||||||||||||||||
DLR - Teilgebiet (Projekt, Vorhaben): | R - Künstliche Intelligenz | ||||||||||||||||
Standort: | Oberpfaffenhofen | ||||||||||||||||
Institute & Einrichtungen: | Institut für Methodik der Fernerkundung > EO Data Science | ||||||||||||||||
Hinterlegt von: | Camero, Dr Andres | ||||||||||||||||
Hinterlegt am: | 27 Sep 2022 13:32 | ||||||||||||||||
Letzte Änderung: | 24 Apr 2024 20:49 |
Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags