Constructing Global Coherence Representations: Identifying Interpretability and Coherences of Transformer Attention in Time Series Data

Autor(en): Schwenke, Leonid
Atzmueller, Martin 
Stichwörter: Computer science; Transformer; Interpretability; Machine learning; Time series; Automatic summarization; Pattern recognition (psychology); Series (stratigraphy); Natural language processing; Artificial intelligence; Coherence (philosophical gambling strategy)
Erscheinungsdatum: 2021
Herausgeber: IEEE
Journal: ieee international conference on data science and advanced analytics
Startseite: 1
Seitenende: 12
DOI: https://doi.org/10.1109/dsaa53316.2021.9564126

Show full item record

Page view(s)

1
Last Week
0
Last month
0
checked on May 24, 2024

Google ScholarTM

Check

Altmetric