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

The field of deep learning has become increasingly important for particlephysics experiments, yielding a multitude of advances, predominantly in eventclassification and reconstruction tasks. Many of these applications have beenadopted from other domains. However, data in the field of physics are unique inthe context of machine learning, insofar as their generation process and thelaws and symmetries they abide by are usually well understood. Most commonlyused deep learning architectures fail at utilizing this available information.In contrast, more traditional likelihood-based methods are capable ofexploiting domain knowledge, but they are often limited by computationalcomplexity. In this contribution, a hybrid approach is presented that utilizesgenerative neural networks to approximate the likelihood, which may then beused in a traditional maximum-likelihood setting. Domain knowledge, such asinvariances and detector characteristics, can easily be incorporated in thisapproach. The hybrid approach is illustrated by the example of eventreconstruction in IceCube.

Combining Maximum-Likelihood with Deep Learning for Event Reconstruction in IceCube