Conference paper Open Access

On the importance of deep learning regularization techniques in knowledge discovery

Ljubinka Sandjakoska; Atanas Hristov; Ana Madevska Bogdanova

MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="">
  <controlfield tag="005">20200120144747.0</controlfield>
  <controlfield tag="001">1447168</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">UIST St Paul the Apostle</subfield>
    <subfield code="a">Atanas Hristov</subfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Ss Cyril and Methodius University</subfield>
    <subfield code="a">Ana Madevska Bogdanova</subfield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">48848</subfield>
    <subfield code="z">md5:f6dbf0843712353c7984c3b5ded81a38</subfield>
    <subfield code="u"> the importance of deep learning regularization techniques in knowledge discovery.docx</subfield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">574277</subfield>
    <subfield code="z">md5:4714e32b47a2eb103f54be87c479639b</subfield>
    <subfield code="u"> the importance of deep learning regularization techniques in knowledge discovery.pdf</subfield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2018-12-19</subfield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="p">user-bigskyearth-conference-2018</subfield>
    <subfield code="o"></subfield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">UIST St Paul the Apostle</subfield>
    <subfield code="a">Ljubinka Sandjakoska</subfield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">On the importance of deep learning regularization techniques in knowledge discovery</subfield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-bigskyearth-conference-2018</subfield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u"></subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2"></subfield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;Nowadays, in the era of complex data, the knowledge discovery process became one of the key challenges in the science. The evolution of the technologies imply evolution of the techniques for dealing with the data. Deep neural networks, as advanced concepts became very popular and can be viewed as tool for improvement of knowledge discovery processes. A motivation for this paper is generalization ability of deep neural network. In an attempt to better understand and to solve the problem of generalization of deep neural networks, we study several regularization techniques. Different regularization techniques, as a solution of overfitting problem, are discussed. The impact of regularization on knowledge discovery process is in the focus of this paper. In order to illustrate the effect of regularization in knowledge discovery, a case study is presented. The case study refers to discovering unknown relationships between molecules in atomic simulation. We propose a dropout method for regularization deep neural network for molecular dynamics simulations. In this paper we show that discovering high level concepts in data, during knowledge discovery, is possible with efficient training of regularized deep neural networks.&lt;/p&gt;</subfield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.1447167</subfield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.1447168</subfield>
    <subfield code="2">doi</subfield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
All versions This version
Views 7272
Downloads 7575
Data volume 35.7 MB35.7 MB
Unique views 6262
Unique downloads 5858


Cite as