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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Accurate simulation of physical processes is crucial for the success ofmodern particle physics. However, simulating the development and interaction ofparticle showers with calorimeter detectors is a time consuming process anddrives the computing needs of large experiments at the LHC and futurecolliders. Recently, generative machine learning models based on deep neuralnetworks have shown promise in speeding up this task by several orders ofmagnitude. We investigate the use of a new architecture -- the BoundedInformation Bottleneck Autoencoder -- for modelling electromagnetic showers inthe central region of the Silicon-Tungsten calorimeter of the proposedInternational Large Detector. Combined with a novel second post-processingnetwork, this approach achieves an accurate simulation of differentialdistributions including for the first time the shape of theminimum-ionizing-particle peak compared to a full GEANT4 simulation for ahigh-granularity calorimeter with 27k simulated channels. The results arevalidated by comparing to established architectures. Our results furtherstrengthen the case of using generative networks for fast simulation anddemonstrate that physically relevant differential distributions can bedescribed with high accuracy.

Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed