June 1, 2021 Report Open Access

Michael Weiss; Paolo Tonella

Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
  <dc:creator>Michael Weiss</dc:creator>
  <dc:creator>Paolo Tonella</dc:creator>
  <dc:date>2021-06-01</dc:date>
  <dc:description>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. We present Uncertainty-Wizard, a tool that allows to quantify such uncertainty and confidence in  artificial neural networks. It is built on top of the industry-leading tf.keras deep learning API and it provides a near-transparent and  easy to understand interface. At the same time, it includes major performance optimizations that we benchmarked on two different machines and different configurations.</dc:description>
  <dc:identifier>https://zenodo.org/record/5055751</dc:identifier>
  <dc:identifier>10.5281/zenodo.5055751</dc:identifier>
  <dc:identifier>oai:zenodo.org:5055751</dc:identifier>
  <dc:relation>info:eu-repo/grantAgreement/EC/H2020/787703/</dc:relation>
  <dc:relation>doi:10.1109/ICST49551.2021.00056</dc:relation>
  <dc:relation>doi:10.5281/zenodo.5055750</dc:relation>
  <dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
  <dc:rights>https://creativecommons.org/licenses/by/4.0/legalcode</dc:rights>
  <dc:title>Uncertainty-Wizard: Fast and User-Friendly Neural Network Uncertainty Quantification</dc:title>
  <dc:type>info:eu-repo/semantics/report</dc:type>
  <dc:type>publication-report</dc:type>
</oai_dc:dc>