Cargando…
A new algorithm for $H\rightarrow\tau\bar{\tau}$ invariant mass reconstruction using Deep Neural Networks
Reconstructing the invariant mass in a Higgs boson decay event containing tau leptons turns out to be a challenging endeavour. The aim of this summer student project is to implement a new algorithm for this task, using deep neural networks and machine learning. The results are compared to SVFit, an...
| Autor principal: | |
|---|---|
| Lenguaje: | eng |
| Publicado: |
2017
|
| Materias: | |
| Acceso en línea: | http://cds.cern.ch/record/2285441 |
| _version_ | 1780955880993325056 |
|---|---|
| author | Dietrich, Felix |
| author_facet | Dietrich, Felix |
| author_sort | Dietrich, Felix |
| collection | CERN |
| description | Reconstructing the invariant mass in a Higgs boson decay event containing tau leptons turns out to be a challenging endeavour. The aim of this summer student project is to implement a new algorithm for this task, using deep neural networks and machine learning. The results are compared to SVFit, an existing algorithm that uses dynamical likelihood techniques. A neural network is found that reaches the accuracy of SVFit at low masses and even surpasses it at higher masses, while at the same time providing results a thousand times faster. |
| id | cern-2285441 |
| institution | Organización Europea para la Investigación Nuclear |
| language | eng |
| publishDate | 2017 |
| record_format | invenio |
| spelling | cern-22854412019-09-30T06:29:59Zhttp://cds.cern.ch/record/2285441engDietrich, FelixA new algorithm for $H\rightarrow\tau\bar{\tau}$ invariant mass reconstruction using Deep Neural NetworksComputing and ComputersParticle Physics - ExperimentReconstructing the invariant mass in a Higgs boson decay event containing tau leptons turns out to be a challenging endeavour. The aim of this summer student project is to implement a new algorithm for this task, using deep neural networks and machine learning. The results are compared to SVFit, an existing algorithm that uses dynamical likelihood techniques. A neural network is found that reaches the accuracy of SVFit at low masses and even surpasses it at higher masses, while at the same time providing results a thousand times faster.CERN-STUDENTS-Note-2017-218oai:cds.cern.ch:22854412017-09-22 |
| spellingShingle | Computing and Computers Particle Physics - Experiment Dietrich, Felix A new algorithm for $H\rightarrow\tau\bar{\tau}$ invariant mass reconstruction using Deep Neural Networks |
| title | A new algorithm for $H\rightarrow\tau\bar{\tau}$ invariant mass reconstruction using Deep Neural Networks |
| title_full | A new algorithm for $H\rightarrow\tau\bar{\tau}$ invariant mass reconstruction using Deep Neural Networks |
| title_fullStr | A new algorithm for $H\rightarrow\tau\bar{\tau}$ invariant mass reconstruction using Deep Neural Networks |
| title_full_unstemmed | A new algorithm for $H\rightarrow\tau\bar{\tau}$ invariant mass reconstruction using Deep Neural Networks |
| title_short | A new algorithm for $H\rightarrow\tau\bar{\tau}$ invariant mass reconstruction using Deep Neural Networks |
| title_sort | new algorithm for $h\rightarrow\tau\bar{\tau}$ invariant mass reconstruction using deep neural networks |
| topic | Computing and Computers Particle Physics - Experiment |
| url | http://cds.cern.ch/record/2285441 |
| work_keys_str_mv | AT dietrichfelix anewalgorithmforhrightarrowtaubartauinvariantmassreconstructionusingdeepneuralnetworks AT dietrichfelix newalgorithmforhrightarrowtaubartauinvariantmassreconstructionusingdeepneuralnetworks |