EUVIMEDEUVIMED entdecken
Crossref

A General Survey on Attention Mechanisms in Deep Learning

Gianni Brauwers, Flavius Frasincar

IEEE Transactions on Knowledge and Data Engineering · 01.04.2023 · 35 (4) · 3279-3298

DOI: 10.1109/tkde.2021.3126456 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, erschienen am 01.04.2023. Verfasst von Gianni Brauwers und 1 weiteren Autor:innen. Die Arbeit wurde bisher 663-mal zitiert (Crossref) und nennt 126 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Attention is an important mechanism that can be employed for a variety of deep learning models across many different domains and tasks. This survey provides an overview of the most important attention mechanisms proposed in the literature. The various attention mechanisms are explained by means of a framework consisting of a general attention model, uniform notation, and a comprehensive taxonomy of attention mechanisms. Furthermore, the various measures for evaluating attention models are reviewed, and methods to characterize the structure of attention models based on the proposed framework are discussed. Last, future work in the field of attention models is considered.

Zitieren

APA

Brauwers, G., & Frasincar, F. (2023). A General Survey on Attention Mechanisms in Deep Learning. IEEE Transactions on Knowledge and Data Engineering, 35(4), 3279-3298. https://doi.org/10.1109/tkde.2021.3126456

Vancouver

Brauwers G, Frasincar F. A General Survey on Attention Mechanisms in Deep Learning. IEEE Transactions on Knowledge and Data Engineering. 2023;35(4):3279-3298. doi:10.1109/tkde.2021.3126456

BibTeX
@article{Brauwers2023,
  author = {Brauwers, Gianni and Frasincar, Flavius},
  title = {A General Survey on Attention Mechanisms in Deep Learning},
  journal = {IEEE Transactions on Knowledge and Data Engineering},
  year = {2023},
  volume = {35},
  number = {4},
  pages = {3279--3298},
  doi = {10.1109/tkde.2021.3126456}
}
Kostenlos starten →