Matches in SemOpenAlex for { <https://semopenalex.org/work/W3135890754> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3135890754 abstract "Abstract The Exa.TrkX project presents a graph neural network (GNN) technique for low-level reconstruction of neutrino interactions in a Liquid Argon Time Projection Chamber (LArTPC). GNNs are still a relatively novel technique, and have shown great promise for similar reconstruction tasks in the Large Hadron Collider (LHC). Graphs describing particle interactions are formed by treating each detector hit as a node, with edges describing the relationships between hits. We utilise a multi-head attention message passing network which performs graph convolutions in order to label each node with a particle type. We present an updated variant of our GNN architecture, with several improvements. After testing the model on more realistic simulation with regions of unresponsive wires, the target was modified from edge classification to node classification in order to increase robustness. Removing edges as a classification target opens up a broader possibility space for edge-forming techniques; we explore the model’s performance across a variety of approaches, such as Delaunay triangulation, kNN, and radius-based methods. We also extend this model to the 3D context, sharing information between detector views. By using reconstructed 3D spacepoints to map detector hits from each wire plane, the model naively constructs 2D representations that are independent yet fully consistent." @default.
- W3135890754 created "2021-03-15" @default.
- W3135890754 creator A5001525854 @default.
- W3135890754 creator A5009438734 @default.
- W3135890754 creator A5011421008 @default.
- W3135890754 creator A5019721001 @default.
- W3135890754 creator A5020033662 @default.
- W3135890754 creator A5030716890 @default.
- W3135890754 creator A5043817735 @default.
- W3135890754 creator A5047611644 @default.
- W3135890754 creator A5053529294 @default.
- W3135890754 creator A5064684941 @default.
- W3135890754 creator A5065122830 @default.
- W3135890754 creator A5066309067 @default.
- W3135890754 creator A5070521079 @default.
- W3135890754 creator A5074672912 @default.
- W3135890754 creator A5076354497 @default.
- W3135890754 creator A5084838541 @default.
- W3135890754 creator A5090493702 @default.
- W3135890754 date "2023-01-01" @default.
- W3135890754 modified "2023-10-18" @default.
- W3135890754 title "Graph Neural Network for Object Reconstruction in Liquid Argon Time Projection Chambers" @default.
- W3135890754 cites W2027598109 @default.
- W3135890754 cites W2579983429 @default.
- W3135890754 cites W3009002854 @default.
- W3135890754 cites W3082428588 @default.
- W3135890754 cites W3195824306 @default.
- W3135890754 cites W3202404106 @default.
- W3135890754 cites W3206565934 @default.
- W3135890754 doi "https://doi.org/10.1088/1742-6596/2438/1/012091" @default.
- W3135890754 hasPublicationYear "2023" @default.
- W3135890754 type Work @default.
- W3135890754 sameAs 3135890754 @default.
- W3135890754 citedByCount "1" @default.
- W3135890754 countsByYear W31358907542021 @default.
- W3135890754 crossrefType "proceedings" @default.
- W3135890754 hasAuthorship W3135890754A5001525854 @default.
- W3135890754 hasAuthorship W3135890754A5009438734 @default.
- W3135890754 hasAuthorship W3135890754A5011421008 @default.
- W3135890754 hasAuthorship W3135890754A5019721001 @default.
- W3135890754 hasAuthorship W3135890754A5020033662 @default.
- W3135890754 hasAuthorship W3135890754A5030716890 @default.
- W3135890754 hasAuthorship W3135890754A5043817735 @default.
- W3135890754 hasAuthorship W3135890754A5047611644 @default.
- W3135890754 hasAuthorship W3135890754A5053529294 @default.
- W3135890754 hasAuthorship W3135890754A5064684941 @default.
- W3135890754 hasAuthorship W3135890754A5065122830 @default.
- W3135890754 hasAuthorship W3135890754A5066309067 @default.
- W3135890754 hasAuthorship W3135890754A5070521079 @default.
- W3135890754 hasAuthorship W3135890754A5074672912 @default.
- W3135890754 hasAuthorship W3135890754A5076354497 @default.
- W3135890754 hasAuthorship W3135890754A5084838541 @default.
- W3135890754 hasAuthorship W3135890754A5090493702 @default.
- W3135890754 hasBestOaLocation W31358907541 @default.
- W3135890754 hasConcept C11413529 @default.
- W3135890754 hasConcept C132525143 @default.
- W3135890754 hasConcept C154945302 @default.
- W3135890754 hasConcept C2781238097 @default.
- W3135890754 hasConcept C31972630 @default.
- W3135890754 hasConcept C41008148 @default.
- W3135890754 hasConcept C50644808 @default.
- W3135890754 hasConcept C57493831 @default.
- W3135890754 hasConcept C80444323 @default.
- W3135890754 hasConceptScore W3135890754C11413529 @default.
- W3135890754 hasConceptScore W3135890754C132525143 @default.
- W3135890754 hasConceptScore W3135890754C154945302 @default.
- W3135890754 hasConceptScore W3135890754C2781238097 @default.
- W3135890754 hasConceptScore W3135890754C31972630 @default.
- W3135890754 hasConceptScore W3135890754C41008148 @default.
- W3135890754 hasConceptScore W3135890754C50644808 @default.
- W3135890754 hasConceptScore W3135890754C57493831 @default.
- W3135890754 hasConceptScore W3135890754C80444323 @default.
- W3135890754 hasLocation W31358907541 @default.
- W3135890754 hasLocation W31358907542 @default.
- W3135890754 hasLocation W31358907543 @default.
- W3135890754 hasLocation W31358907544 @default.
- W3135890754 hasLocation W31358907545 @default.
- W3135890754 hasLocation W31358907546 @default.
- W3135890754 hasLocation W31358907547 @default.
- W3135890754 hasLocation W31358907548 @default.
- W3135890754 hasOpenAccess W3135890754 @default.
- W3135890754 hasPrimaryLocation W31358907541 @default.
- W3135890754 hasRelatedWork W1837097281 @default.
- W3135890754 hasRelatedWork W1966410754 @default.
- W3135890754 hasRelatedWork W2007544051 @default.
- W3135890754 hasRelatedWork W2016398835 @default.
- W3135890754 hasRelatedWork W2095705906 @default.
- W3135890754 hasRelatedWork W2325242284 @default.
- W3135890754 hasRelatedWork W2363840281 @default.
- W3135890754 hasRelatedWork W258625772 @default.
- W3135890754 hasRelatedWork W2789220062 @default.
- W3135890754 hasRelatedWork W2975200075 @default.
- W3135890754 isParatext "false" @default.
- W3135890754 isRetracted "false" @default.
- W3135890754 magId "3135890754" @default.
- W3135890754 workType "paratext" @default.