Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896410853> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2896410853 abstract "Author(s): Farrell, Steven; Calafiura, Paolo; Mudigonda, Mayur; Prabhat; Anderson, Dustin; Vlimant, Jean-Roch; Zheng, Stephan; Bendavid, Josh; Spiropulu, Maria; Cerati, Giuseppe; Gray, Lindsey; Kowalkowski, Jim; Spentzouris, Panagiotis; Tsaris, Aristeidis | Abstract: For the past year, the HEP.TrkX project has been investigating machine learning solutions to LHC particle track reconstruction problems. A variety of models were studied that drew inspiration from computer vision applications and operated on an image-like representation of tracking detector data. While these approaches have shown some promise, image-based methods face challenges in scaling up to realistic HL-LHC data due to high dimensionality and sparsity. In contrast, models that can operate on the spacepoint representation of track measurements (hits) can exploit the structure of the data to solve tasks efficiently. In this paper we will show two sets of new deep learning models for reconstructing tracks using space-point data arranged as sequences or connected graphs. In the first set of models, Recurrent Neural Networks (RNNs) are used to extrapolate, build, and evaluate track candidates akin to Kalman Filter algorithms. Such models can express their own uncertainty when trained with an appropriate likelihood loss function. The second set of models use Graph Neural Networks (GNNs) for the tasks of hit classification and segment classification. These models read a graph of connected hits and compute features on the nodes and edges. They adaptively learn which hit connections are important and which are spurious. The models are scaleable with simple architecture and relatively few parameters. Results for all models will be presented on ACTS generic detector simulated data." @default.
- W2896410853 created "2018-10-26" @default.
- W2896410853 creator A5006493183 @default.
- W2896410853 creator A5009438734 @default.
- W2896410853 creator A5019721001 @default.
- W2896410853 creator A5031913929 @default.
- W2896410853 creator A5037040418 @default.
- W2896410853 creator A5041381106 @default.
- W2896410853 creator A5046383338 @default.
- W2896410853 creator A5059845410 @default.
- W2896410853 creator A5059906105 @default.
- W2896410853 creator A5066309067 @default.
- W2896410853 creator A5070521079 @default.
- W2896410853 creator A5074672912 @default.
- W2896410853 creator A5076354497 @default.
- W2896410853 creator A5081549062 @default.
- W2896410853 date "2018-10-14" @default.
- W2896410853 modified "2023-09-27" @default.
- W2896410853 title "Novel deep learning methods for track reconstruction" @default.
- W2896410853 hasPublicationYear "2018" @default.
- W2896410853 type Work @default.
- W2896410853 sameAs 2896410853 @default.
- W2896410853 citedByCount "20" @default.
- W2896410853 countsByYear W28964108532018 @default.
- W2896410853 countsByYear W28964108532019 @default.
- W2896410853 countsByYear W28964108532020 @default.
- W2896410853 countsByYear W28964108532021 @default.
- W2896410853 countsByYear W28964108532022 @default.
- W2896410853 crossrefType "posted-content" @default.
- W2896410853 hasAuthorship W2896410853A5006493183 @default.
- W2896410853 hasAuthorship W2896410853A5009438734 @default.
- W2896410853 hasAuthorship W2896410853A5019721001 @default.
- W2896410853 hasAuthorship W2896410853A5031913929 @default.
- W2896410853 hasAuthorship W2896410853A5037040418 @default.
- W2896410853 hasAuthorship W2896410853A5041381106 @default.
- W2896410853 hasAuthorship W2896410853A5046383338 @default.
- W2896410853 hasAuthorship W2896410853A5059845410 @default.
- W2896410853 hasAuthorship W2896410853A5059906105 @default.
- W2896410853 hasAuthorship W2896410853A5066309067 @default.
- W2896410853 hasAuthorship W2896410853A5070521079 @default.
- W2896410853 hasAuthorship W2896410853A5074672912 @default.
- W2896410853 hasAuthorship W2896410853A5076354497 @default.
- W2896410853 hasAuthorship W2896410853A5081549062 @default.
- W2896410853 hasConcept C108583219 @default.
- W2896410853 hasConcept C119857082 @default.
- W2896410853 hasConcept C132525143 @default.
- W2896410853 hasConcept C153180895 @default.
- W2896410853 hasConcept C154945302 @default.
- W2896410853 hasConcept C157286648 @default.
- W2896410853 hasConcept C31972630 @default.
- W2896410853 hasConcept C41008148 @default.
- W2896410853 hasConcept C52421305 @default.
- W2896410853 hasConcept C80444323 @default.
- W2896410853 hasConcept C97256817 @default.
- W2896410853 hasConceptScore W2896410853C108583219 @default.
- W2896410853 hasConceptScore W2896410853C119857082 @default.
- W2896410853 hasConceptScore W2896410853C132525143 @default.
- W2896410853 hasConceptScore W2896410853C153180895 @default.
- W2896410853 hasConceptScore W2896410853C154945302 @default.
- W2896410853 hasConceptScore W2896410853C157286648 @default.
- W2896410853 hasConceptScore W2896410853C31972630 @default.
- W2896410853 hasConceptScore W2896410853C41008148 @default.
- W2896410853 hasConceptScore W2896410853C52421305 @default.
- W2896410853 hasConceptScore W2896410853C80444323 @default.
- W2896410853 hasConceptScore W2896410853C97256817 @default.
- W2896410853 hasLocation W28964108531 @default.
- W2896410853 hasOpenAccess W2896410853 @default.
- W2896410853 hasPrimaryLocation W28964108531 @default.
- W2896410853 hasRelatedWork W2098406858 @default.
- W2896410853 hasRelatedWork W2116341502 @default.
- W2896410853 hasRelatedWork W2151512268 @default.
- W2896410853 hasRelatedWork W2163097950 @default.
- W2896410853 hasRelatedWork W2624881227 @default.
- W2896410853 hasRelatedWork W2805516822 @default.
- W2896410853 hasRelatedWork W2896693058 @default.
- W2896410853 hasRelatedWork W2915621743 @default.
- W2896410853 hasRelatedWork W2916639378 @default.
- W2896410853 hasRelatedWork W2939979914 @default.
- W2896410853 hasRelatedWork W2952915411 @default.
- W2896410853 hasRelatedWork W2964121744 @default.
- W2896410853 hasRelatedWork W2975089235 @default.
- W2896410853 hasRelatedWork W2999026142 @default.
- W2896410853 hasRelatedWork W3002851826 @default.
- W2896410853 hasRelatedWork W3013398575 @default.
- W2896410853 hasRelatedWork W3038360393 @default.
- W2896410853 hasRelatedWork W3087865810 @default.
- W2896410853 hasRelatedWork W3101493857 @default.
- W2896410853 hasRelatedWork W3101501459 @default.
- W2896410853 isParatext "false" @default.
- W2896410853 isRetracted "false" @default.
- W2896410853 magId "2896410853" @default.
- W2896410853 workType "article" @default.