KIT | KIT-Bibliothek | Impressum | Datenschutz

When to Use Which Neural Network? Finding the Right Neural Network Architecture for a Research Problem

Färber, Michael ORCID iD icon 1; Weber, Nicolas
1 Institut für Angewandte Informatik und Formale Beschreibungsverfahren (AIFB), Karlsruher Institut für Technologie (KIT)

Abstract:

Considering the increasing rate of scientific papers published in recent years, for researchers throughout all disciplines it has become a challenge to keep track of which latest scientific methods are suitable for which applications. In particular, an unmanageable amount of neural network architectures has been published. In this paper, we propose the task of recommending neural network architectures based on textual problem descriptions. We frame the recommendation as a text classification task and develop appropriate text classification models for this task. In experiments based on three data sets, we find that an SVM classifier outperforms a more complex model based on BERT. Overall, we give evidence that neural network architecture recommendation is a nontrivial but gainful research topic.


Zugehörige Institution(en) am KIT Institut für Angewandte Informatik und Formale Beschreibungsverfahren (AIFB)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2022
Sprache Englisch
Identifikator ISSN: 1613-0073
KITopen-ID: 1000149453
Erschienen in SDU 2022: Scientific Document Understanding 2022 ; Proceedings of the Workshop on Scientific Document Understanding ; co-located with 36th AAAI Conference on Artificial Inteligence (AAAI 2022) ; Remote, March 1, 2022. Ed.: A. P. Ben Veyseh
Veranstaltung Workshop on Scientific Document Understanding (SDU 2022), Online, 01.03.2022
Verlag CEUR-WS.org
Serie CEUR Workshop Proceedings ; 3164
Externe Relationen Abstract/Volltext
Schlagwörter recommender systems, machine learning, neural network architectures, open science
Nachgewiesen in Scopus
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page