June 1, 2021 Report Open Access

Michael Weiss; Paolo Tonella

DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.5055751</identifier>
  <creators>
    <creator>
      <creatorName>Michael Weiss</creatorName>
      <affiliation>Università della Svizzera italiana</affiliation>
    </creator>
    <creator>
      <creatorName>Paolo Tonella</creatorName>
      <affiliation>Università della Svizzera italiana</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Uncertainty-Wizard: Fast and User-Friendly Neural Network Uncertainty Quantification</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2021</publicationYear>
  <dates>
    <date dateType="Issued">2021-06-01</date>
  </dates>
  <resourceType resourceTypeGeneral="Report"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/5055751</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsObsoletedBy">10.1109/ICST49551.2021.00056</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.5055750</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;Uncertainty and confidence have been shown to be useful metrics in a wide variety of techniques proposed for deep learning testing, including test data selection and system supervision.&amp;nbsp;We present Uncertainty-Wizard, a tool that allows to quantify such uncertainty and confidence in&amp;nbsp; artificial neural networks.&amp;nbsp;It is built on top of the industry-leading tf.keras deep learning API and it provides a near-transparent and&amp;nbsp; easy to understand interface.&amp;nbsp;At the same time, it includes major performance optimizations that we benchmarked on two different machines and different configurations.&lt;/p&gt;</description>
  </descriptions>
  <fundingReferences>
    <fundingReference>
      <funderName>European Commission</funderName>
      <funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/100010661</funderIdentifier>
      <awardNumber awardURI="info:eu-repo/grantAgreement/EC/H2020/787703/">787703</awardNumber>
      <awardTitle>Self-assessment Oracles for Anticipatory Testing</awardTitle>
    </fundingReference>
  </fundingReferences>
</resource>