Bachelor Thesis Open Access

Illustration of the Neural Network Learning Process during Training

Heine, Greta Sophie

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="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2019-11-04</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">neural network, training, Taylor expansion</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">7743959</subfield>
    <subfield code="u">https://publish.etp.kit.edu/record/21984/files/BA_greta_heine.pdf</subfield>
    <subfield code="z">md5:5ad0a4cc8d8f3ee063123e8878fe5ac5</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;This thesis enhances the understanding of Neural Network (NN) trainings by&lt;br&gt;
investigation of the learning process especially focusing on the dependence&lt;br&gt;
of the NN output on the input space for given tasks. For this purpose, the&lt;br&gt;
NN function is decomposed into a Taylor expansion. The Taylor coefficients&lt;br&gt;
serve as a metric to illustrate the influence of input space features on the&lt;br&gt;
output at each step of the training. Both, the arithmetic mean values of the&lt;br&gt;
Taylor coefficients and their dependence on each point of the input space are&lt;br&gt;
investigated, giving new insights into the decision taking of NNs.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">thesis</subfield>
    <subfield code="b">bachelor-thesis</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Wolf, Roger</subfield>
    <subfield code="u">KIT/ETP</subfield>
    <subfield code="4">ths</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Quast, Guenther</subfield>
    <subfield code="u">KIT/ETP</subfield>
    <subfield code="4">ths</subfield>
  </datafield>
  <controlfield tag="005">20200825130929.0</controlfield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="a">Heine, Greta Sophie</subfield>
    <subfield code="u">KIT/ETP</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-computing</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-etp</subfield>
  </datafield>
  <controlfield tag="001">21984</controlfield>
  <datafield tag="041" ind1=" " ind2=" ">
    <subfield code="a">eng</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Illustration of the Neural Network Learning Process during Training</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="o">oai:publish.etp.kit.edu:21984</subfield>
    <subfield code="p">user-computing</subfield>
    <subfield code="p">user-etp</subfield>
  </datafield>
</record>
Publication date:
November 4, 2019
Keyword(s):
neural network, training, Taylor expansion
Awarding University:
Karlsruhe Institute of Technology (KIT)
Report Number:
ETP-BACHELOR-KA/2019-17
Communities:

Cite as

Export