1. ZHAW digitalcollection
  2. School of Engineering
  3. Publikationen
  4. Publikationen School of Engineering
Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-20804
Full metadata record
DC FieldValueLanguage
dc.contributor.authorTuggener, Lukas-
dc.contributor.authorAmirian, Mohammadreza-
dc.contributor.authorBenites de Azevedo e Souza, Fernando-
dc.contributor.authorvon Däniken, Pius-
dc.contributor.authorGupta, Prakhar-
dc.contributor.authorSchilling, Frank-Peter-
dc.contributor.authorStadelmann, Thilo-
dc.date.accessioned2020-11-12T13:24:47Z-
dc.date.available2020-11-12T13:24:47Z-
dc.date.issued2020-11-06-
dc.identifier.issn2673-2688de_CH
dc.identifier.urihttps://digitalcollection.zhaw.ch/handle/11475/20804-
dc.description.abstractWe present an extensive evaluation of a wide variety of promising design patterns for automated deep-learning (AutoDL) methods, organized according to the problem categories of the 2019 AutoDL challenges, which set the task of optimizing both model accuracy and search efficiency under tight time and computing constraints. We propose structured empirical evaluations as the most promising avenue to obtain design principles for deep-learning systems due to the absence of strong theoretical support. From these evaluations, we distill relevant patterns which give rise to neural network design recommendations. In particular, we establish (a) that very wide fully connected layers learn meaningful features faster; we illustrate (b) how the lack of pretraining in audio processing can be compensated by architecture search; we show (c) that in text processing deep-learning-based methods only pull ahead of traditional methods for short text lengths with less than a thousand characters under tight resource limitations; and lastly we present (d) evidence that in very data- and computing-constrained settings, hyperparameter tuning of more traditional machine-learning methods outperforms deep-learning systems.de_CH
dc.language.isoende_CH
dc.publisherMDPIde_CH
dc.relation.ispartofAIde_CH
dc.rightshttp://creativecommons.org/licenses/by/4.0/de_CH
dc.subjectAutomated machine learningde_CH
dc.subjectArchitecture designde_CH
dc.subjectComputer visionde_CH
dc.subjectAudio processingde_CH
dc.subjectNatural language processingde_CH
dc.subjectWeakly supervised learningde_CH
dc.subject.ddc006: Spezielle Computerverfahrende_CH
dc.titleDesign patterns for resource-constrained automated deep-learning methodsde_CH
dc.typeBeitrag in wissenschaftlicher Zeitschriftde_CH
dcterms.typeTextde_CH
zhaw.departementSchool of Engineeringde_CH
zhaw.organisationalunitInstitut für Informatik (InIT)de_CH
dc.identifier.doi10.3390/ai1040031de_CH
dc.identifier.doi10.21256/zhaw-20804-
zhaw.funding.euNode_CH
zhaw.issue4de_CH
zhaw.originated.zhawYesde_CH
zhaw.pages.end538de_CH
zhaw.pages.start510de_CH
zhaw.publication.statuspublishedVersionde_CH
zhaw.volume1de_CH
zhaw.publication.reviewPeer review (Publikation)de_CH
zhaw.webfeedDatalabde_CH
zhaw.webfeedInformation Engineeringde_CH
zhaw.webfeedSoftware Systemsde_CH
zhaw.webfeedZHAW digitalde_CH
zhaw.webfeedNatural Language Processingde_CH
zhaw.webfeedMachine Perception and Cognitionde_CH
zhaw.webfeedIntelligent Vision Systemsde_CH
zhaw.funding.zhawAda – Advanced Algorithms for an Artificial Data Analystde_CH
zhaw.author.additionalNode_CH
zhaw.display.portraitYesde_CH
Appears in collections:Publikationen School of Engineering

Files in This Item:
File Description SizeFormat 
2020_Tuggener-etal_Design-patterns-deep-learning-methods_AI.pdf6.28 MBAdobe PDFThumbnail
View/Open
Show simple item record
Tuggener, L., Amirian, M., Benites de Azevedo e Souza, F., von Däniken, P., Gupta, P., Schilling, F.-P., & Stadelmann, T. (2020). Design patterns for resource-constrained automated deep-learning methods. Ai, 1(4), 510–538. https://doi.org/10.3390/ai1040031
Tuggener, L. et al. (2020) ‘Design patterns for resource-constrained automated deep-learning methods’, AI, 1(4), pp. 510–538. Available at: https://doi.org/10.3390/ai1040031.
L. Tuggener et al., “Design patterns for resource-constrained automated deep-learning methods,” AI, vol. 1, no. 4, pp. 510–538, Nov. 2020, doi: 10.3390/ai1040031.
TUGGENER, Lukas, Mohammadreza AMIRIAN, Fernando BENITES DE AZEVEDO E SOUZA, Pius VON DÄNIKEN, Prakhar GUPTA, Frank-Peter SCHILLING und Thilo STADELMANN, 2020. Design patterns for resource-constrained automated deep-learning methods. AI. 6 November 2020. Bd. 1, Nr. 4, S. 510–538. DOI 10.3390/ai1040031
Tuggener, Lukas, Mohammadreza Amirian, Fernando Benites de Azevedo e Souza, Pius von Däniken, Prakhar Gupta, Frank-Peter Schilling, and Thilo Stadelmann. 2020. “Design Patterns for Resource-Constrained Automated Deep-Learning Methods.” Ai 1 (4): 510–38. https://doi.org/10.3390/ai1040031.
Tuggener, Lukas, et al. “Design Patterns for Resource-Constrained Automated Deep-Learning Methods.” Ai, vol. 1, no. 4, Nov. 2020, pp. 510–38, https://doi.org/10.3390/ai1040031.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.