Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387442017> ?p ?o ?g. }
Showing items 1 to 55 of
55
with 100 items per page.
- W4387442017 abstract "Abstract Future surveys such as the Legacy Survey of Space and Time (LSST) of the Vera C. Rubin Observatory will observe an order of magnitude more astrophysical transient events than any previous survey before. With this deluge of photometric data, it will be impossible for all such events to be classified by humans alone. Recent efforts have sought to leverage machine learning methods to tackle the challenge of astronomical transient classification, with ever improving success. Transformers are a recently developed deep learning architecture, first proposed for natural language processing, that have shown a great deal of recent success. In this work we develop a new transformer architecture, which uses multi-head self attention at its core, for general multi-variate time-series data. Furthermore, the proposed time-series transformer architecture supports the inclusion of an arbitrary number of additional features, while also offering interpretability. We apply the time-series transformer to the task of photometric classification, minimising the reliance of expert domain knowledge for feature selection, while achieving results comparable to state-of-the-art photometric classification methods. We achieve a logarithmic-loss of 0.507 on imbalanced data in a representative setting using data from the Photometric LSST Astronomical Time-Series Classification Challenge (PLAsTiCC). Moreover, we achieve a micro-averaged receiver operating characteristic area under curve of 0.98 and micro-averaged precision-recall area under curve of 0.87." @default.
- W4387442017 created "2023-10-10" @default.
- W4387442017 creator A5012959482 @default.
- W4387442017 creator A5014128572 @default.
- W4387442017 date "2023-10-09" @default.
- W4387442017 modified "2023-10-11" @default.
- W4387442017 title "Paying attention to astronomical transients: Introducing the time-series transformer for photometric classification" @default.
- W4387442017 doi "https://doi.org/10.1093/rasti/rzad046" @default.
- W4387442017 hasPublicationYear "2023" @default.
- W4387442017 type Work @default.
- W4387442017 citedByCount "0" @default.
- W4387442017 crossrefType "journal-article" @default.
- W4387442017 hasAuthorship W4387442017A5012959482 @default.
- W4387442017 hasAuthorship W4387442017A5014128572 @default.
- W4387442017 hasBestOaLocation W43874420171 @default.
- W4387442017 hasConcept C119599485 @default.
- W4387442017 hasConcept C119857082 @default.
- W4387442017 hasConcept C123657996 @default.
- W4387442017 hasConcept C124101348 @default.
- W4387442017 hasConcept C127413603 @default.
- W4387442017 hasConcept C142362112 @default.
- W4387442017 hasConcept C153349607 @default.
- W4387442017 hasConcept C154945302 @default.
- W4387442017 hasConcept C165801399 @default.
- W4387442017 hasConcept C2781067378 @default.
- W4387442017 hasConcept C41008148 @default.
- W4387442017 hasConcept C66322947 @default.
- W4387442017 hasConceptScore W4387442017C119599485 @default.
- W4387442017 hasConceptScore W4387442017C119857082 @default.
- W4387442017 hasConceptScore W4387442017C123657996 @default.
- W4387442017 hasConceptScore W4387442017C124101348 @default.
- W4387442017 hasConceptScore W4387442017C127413603 @default.
- W4387442017 hasConceptScore W4387442017C142362112 @default.
- W4387442017 hasConceptScore W4387442017C153349607 @default.
- W4387442017 hasConceptScore W4387442017C154945302 @default.
- W4387442017 hasConceptScore W4387442017C165801399 @default.
- W4387442017 hasConceptScore W4387442017C2781067378 @default.
- W4387442017 hasConceptScore W4387442017C41008148 @default.
- W4387442017 hasConceptScore W4387442017C66322947 @default.
- W4387442017 hasLocation W43874420171 @default.
- W4387442017 hasOpenAccess W4387442017 @default.
- W4387442017 hasPrimaryLocation W43874420171 @default.
- W4387442017 hasRelatedWork W1986582023 @default.
- W4387442017 hasRelatedWork W2806259446 @default.
- W4387442017 hasRelatedWork W2883749686 @default.
- W4387442017 hasRelatedWork W2905433371 @default.
- W4387442017 hasRelatedWork W4310278675 @default.
- W4387442017 hasRelatedWork W4311431240 @default.
- W4387442017 hasRelatedWork W4312407344 @default.
- W4387442017 hasRelatedWork W4315864862 @default.
- W4387442017 hasRelatedWork W4361193272 @default.
- W4387442017 hasRelatedWork W2963326959 @default.
- W4387442017 isParatext "false" @default.
- W4387442017 isRetracted "false" @default.
- W4387442017 workType "article" @default.