Bitte benutzen Sie diese Kennung, um auf die Ressource zu verweisen:
https://doi.org/10.21256/zhaw-18993| Publikationstyp: | Konferenz: Paper |
| Art der Begutachtung: | Peer review (Abstract) |
| Titel: | Hyperparameter tuning for deep learning in natural language processing |
| Autor/-in: | Aghaebrahimian, Ahmad Cieliebak, Mark |
| et. al: | No |
| DOI: | 10.21256/zhaw-18993 |
| Angaben zur Konferenz: | 4th Swiss Text Analytics Conference (SwissText 2019), Winterthur, June 18-19 2019 |
| Erscheinungsdatum: | 2019 |
| Verlag / Hrsg. Institution: | Swisstext |
| Sprache: | Englisch |
| Fachgebiet (DDC): | 006: Spezielle Computerverfahren |
| Zusammenfassung: | Deep Neural Networks have advanced rapidly over the past several years. However, it still seems like a black art for many people to make use of them efficiently. The reason for this complexity is that obtaining a consistent and outstanding result from a deep architecture requires optimizing many parameters known as hyperparameters. Hyperparameter tuning is an essential task in deep learning, which can make significant changes in network performance. This paper is the essence of over 3000 GPU hours on optimizing a network for a text classification task on a wide array of hyperparameters. We provide a list of hyperparameters to tune in addition to their tuning impact on the network performance. The hope is that such a listing will provide the interested researchers a mean to prioritize their efforts and to modify their deep architecture for getting the best performance with the least effort. |
| URI: | https://digitalcollection.zhaw.ch/handle/11475/18993 |
| Volltext Version: | Publizierte Version |
| Lizenz (gemäss Verlagsvertrag): | Keine Angabe |
| Departement: | School of Engineering |
| Organisationseinheit: | Institut für Informatik (InIT) |
| Enthalten in den Sammlungen: | Publikationen School of Engineering |
Dateien zu dieser Ressource:
| Datei | Beschreibung | Größe | Format | |
|---|---|---|---|---|
| swisstext19_Hyperparameters.pdf | Hyperparameter Tuning for Deep Learning in Natural Language Processing | 171.02 kB | Adobe PDF |  Öffnen/Anzeigen |
Zur Langanzeige
Aghaebrahimian, A., & Cieliebak, M. (2019). Hyperparameter tuning for deep learning in natural language processing. 4th Swiss Text Analytics Conference (SwissText 2019), Winterthur, June 18-19 2019. https://doi.org/10.21256/zhaw-18993
Aghaebrahimian, A. and Cieliebak, M. (2019) ‘Hyperparameter tuning for deep learning in natural language processing’, in 4th Swiss Text Analytics Conference (SwissText 2019), Winterthur, June 18-19 2019. Swisstext. Available at: https://doi.org/10.21256/zhaw-18993.
A. Aghaebrahimian and M. Cieliebak, “Hyperparameter tuning for deep learning in natural language processing,” in 4th Swiss Text Analytics Conference (SwissText 2019), Winterthur, June 18-19 2019, 2019. doi: 10.21256/zhaw-18993.
AGHAEBRAHIMIAN, Ahmad und Mark CIELIEBAK, 2019. Hyperparameter tuning for deep learning in natural language processing. In: 4th Swiss Text Analytics Conference (SwissText 2019), Winterthur, June 18-19 2019. Conference paper. Swisstext. 2019
Aghaebrahimian, Ahmad, and Mark Cieliebak. 2019. “Hyperparameter Tuning for Deep Learning in Natural Language Processing.” Conference paper. In 4th Swiss Text Analytics Conference (SwissText 2019), Winterthur, June 18-19 2019. Swisstext. https://doi.org/10.21256/zhaw-18993.
Aghaebrahimian, Ahmad, and Mark Cieliebak. “Hyperparameter Tuning for Deep Learning in Natural Language Processing.” 4th Swiss Text Analytics Conference (SwissText 2019), Winterthur, June 18-19 2019, Swisstext, 2019, https://doi.org/10.21256/zhaw-18993.
Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt.