Search: onr:"swepub:oai:DiVA.org:uu-518507" >
Combining Maximum-L...
Combining Maximum-Likelihood with Deep Learning for Event Reconstruction in IceCube
-
- Abbasi, R. (author)
- Loyola Univ Chicago, Dept Phys, Chicago, IL 60660 USA
-
- Botner, Olga (author)
- Uppsala universitet,Högenergifysik
-
- Burgman, Alexander (author)
- Uppsala universitet,Högenergifysik,FREIA
-
show more...
-
- Glaser, Christian (author)
- Uppsala universitet,Högenergifysik
-
- Hallgren, Allan, 1951- (author)
- Uppsala universitet,Högenergifysik
-
- O'Sullivan, Erin (author)
- Uppsala universitet,Högenergifysik
-
- Pérez de los Heros, Carlos (author)
- Uppsala universitet,Högenergifysik
-
- Sharma, Ankur (author)
- Uppsala universitet,Högenergifysik
-
- Valtonen-Mattila, Nora (author)
- Uppsala universitet,Högenergifysik
-
- Zhang, Z. (author)
- SUNY Stony Brook, Dept Phys & Astron, Stony Brook, NY 11794 USA
-
show less...
-
(creator_code:org_t)
- Trieste, Italy : Sissa Medialab Srl, 2022
- 2022
- English.
-
In: 37th International Cosmic Ray Conference (ICRC 2021). - Trieste, Italy : Sissa Medialab Srl.
- Related links:
-
https://doi.org/10.2...
-
show more...
-
https://uu.diva-port... (primary) (Raw object)
-
https://pos.sissa.it...
-
https://urn.kb.se/re...
-
https://doi.org/10.2...
-
show less...
Abstract
Subject headings
Close
- The field of deep learning has become increasingly important for particle physics experiments, yielding a multitude of advances, predominantly in event classification and reconstruction tasks. Many of these applications have been adopted from other domains. However, data in the field of physics are unique in the context of machine learning, insofar as their generation process and the laws and symmetries they abide by are usually well understood. Most commonly used deep learning architectures fail at utilizing this available information. In contrast, more traditional likelihood-based methods are capable of exploiting domain knowledge, but they are often limited by computational complexity.In this contribution, a hybrid approach is presented that utilizes generative neural networks to approximate the likelihood, which may then be used in a traditional maximum-likelihood setting. Domain knowledge, such as invariances and detector characteristics, can easily be incorporated in this approach. The hybrid approach is illustrated by the example of event reconstruction in IceCube.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Annan data- och informationsvetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Other Computer and Information Science (hsv//eng)
- NATURVETENSKAP -- Fysik -- Annan fysik (hsv//swe)
- NATURAL SCIENCES -- Physical Sciences -- Other Physics Topics (hsv//eng)
Publication and Content Type
- ref (subject category)
- kon (subject category)
To the university's database