July 27, 2021 Master Thesis Open Access

Sowa, Lars

MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-belle2</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-etp</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="a">Sowa, Lars</subfield>
    <subfield code="u">KIT/ETP</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2021-07-27</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="o">oai:publish.etp.kit.edu:22060</subfield>
    <subfield code="p">user-belle2</subfield>
    <subfield code="p">user-etp</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Deep Continuum Suppression with Predictive Uncertainties at the Belle II Experiment</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">5849212</subfield>
    <subfield code="u">https://publish.etp.kit.edu/record/22060/files/LS_DeepContSupp_Thesis.pdf</subfield>
    <subfield code="z">md5:a08a5420a9800e5d6311fe1e51debec6</subfield>
  </datafield>
  <controlfield tag="001">22060</controlfield>
  <datafield tag="041" ind1=" " ind2=" ">
    <subfield code="a">eng</subfield>
  </datafield>
  <controlfield tag="005">20210909160933.0</controlfield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Continuum Suppression</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Deep Learning</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Uncertainties</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Decorrelation</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Self-Attention</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Kahn, James</subfield>
    <subfield code="u">KIT/SCC</subfield>
    <subfield code="4">ths</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Goldenzweig, Pablo</subfield>
    <subfield code="u">KIT/ETP</subfield>
    <subfield code="4">ths</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Husemann, Ulrich</subfield>
    <subfield code="u">KIT/ETP</subfield>
    <subfield code="4">ths</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Quast, Günter</subfield>
    <subfield code="u">KIT/ETP</subfield>
    <subfield code="4">ths</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;The SuperKEKB collider in Japan accelerates&lt;br&gt;
electrons and positrons which collide at an energy of 11 GeV aiming to produce B meson&lt;br&gt;
pairs. To analyse the properties of a B meson, it gets recombined from its decay daughters.&lt;br&gt;
Since there are a lot of background events that mimic the signature of a B meson, it is&lt;br&gt;
important to suppress these events. Such a suppression is called Continuum Suppression. This work aims to further improve the Deep Continuum Suppression, which is perfromed by a Multilayer Perceptron (MLP), by three points: Firstly, an MLP needs a fixed order for input particles. Therefore, this thesis&lt;br&gt;
presents a reliable, self-attention-based input mechanism which allows for invariance under&lt;br&gt;
the particle order. Secondly, to guarantee certainty about the prediction of deep learning models, there is a&lt;br&gt;
high interest in models with predictive uncertainties. This is addressed using the concept&lt;br&gt;
of Deep Ensembles to predict uncertainties of continuum classifications.&lt;br&gt;
Finally, the use of vertex information for the training of a model leads to a bias in&lt;br&gt;
certain analysis variables. Since this could lead to falsification of further studies, a Distance&lt;br&gt;
Correlation is used to decorrelate the Continuum Suppression model from third variables.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">thesis</subfield>
    <subfield code="b">master-thesis</subfield>
  </datafield>
</record>