English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

For the past year, the HEP.TrkX project has been investigating machinelearning solutions to LHC particle track reconstruction problems. A variety ofmodels were studied that drew inspiration from computer vision applications andoperated on an image-like representation of tracking detector data. While theseapproaches have shown some promise, image-based methods face challenges inscaling up to realistic HL-LHC data due to high dimensionality and sparsity. Incontrast, models that can operate on the spacepoint representation of trackmeasurements ("hits") can exploit the structure of the data to solve tasksefficiently. In this paper we will show two sets of new deep learning modelsfor reconstructing tracks using space-point data arranged as sequences orconnected graphs. In the first set of models, Recurrent Neural Networks (RNNs)are used to extrapolate, build, and evaluate track candidates akin to KalmanFilter algorithms. Such models can express their own uncertainty when trainedwith an appropriate likelihood loss function. The second set of models useGraph Neural Networks (GNNs) for the tasks of hit classification and segmentclassification. These models read a graph of connected hits and computefeatures on the nodes and edges. They adaptively learn which hit connectionsare important and which are spurious. The models are scaleable with simplearchitecture and relatively few parameters. Results for all models will bepresented on ACTS generic detector simulated data.

Novel deep learning methods for track reconstruction