Report Open Access

Fail-Safe Execution of Deep Learning based Systems through Uncertainty Monitoring

Michael Weiss; Paolo Tonella


DCAT Export

<?xml version='1.0' encoding='utf-8'?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:adms="http://www.w3.org/ns/adms#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dct="http://purl.org/dc/terms/" xmlns:dctype="http://purl.org/dc/dcmitype/" xmlns:dcat="http://www.w3.org/ns/dcat#" xmlns:duv="http://www.w3.org/ns/duv#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:frapo="http://purl.org/cerif/frapo/" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:gsp="http://www.opengis.net/ont/geosparql#" xmlns:locn="http://www.w3.org/ns/locn#" xmlns:org="http://www.w3.org/ns/org#" xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:prov="http://www.w3.org/ns/prov#" xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#" xmlns:schema="http://schema.org/" xmlns:skos="http://www.w3.org/2004/02/skos/core#" xmlns:vcard="http://www.w3.org/2006/vcard/ns#" xmlns:wdrs="http://www.w3.org/2007/05/powder-s#">
  <rdf:Description rdf:about="https://doi.org/10.5281/zenodo.5055710">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.5281/zenodo.5055710</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.5055710"/>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Michael Weiss</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Università della Svizzera italiana</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Paolo Tonella</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Università della Svizzera italiana</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>Fail-Safe Execution of Deep Learning based Systems through Uncertainty Monitoring</dct:title>
    <dct:publisher>
      <foaf:Agent>
        <foaf:name>Zenodo</foaf:name>
      </foaf:Agent>
    </dct:publisher>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#gYear">2020</dct:issued>
    <frapo:isFundedBy rdf:resource="info:eu-repo/grantAgreement/EC/H2020/787703/"/>
    <schema:funder>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/100010661</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </schema:funder>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2020-09-01</dct:issued>
    <owl:sameAs rdf:resource="https://zenodo.org/record/5055710"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/5055710</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:isReplacedBy rdf:resource="https://doi.org/10.1109/ICST49551.2021.00015"/>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.5055709"/>
    <dct:description>&lt;p&gt;Modern software systems rely on Deep Neural Networks (DNN) when processing complex, unstructured inputs, such as images, videos, natural language texts or audio signals.&amp;nbsp;Provided the intractably large size of such input spaces, the intrinsic limitations of learning algorithms&amp;nbsp; and the ambiguity about the expected predictions for some of the inputs, not only there is no guarantee that DNN&amp;#39;s predictions are always correct, but rather developers must safely assume a low, though not negligible, error probability.&amp;nbsp;A fail-safe Deep Learning based System (DLS) is one equipped to handle DNN faults by means of a supervisor, capable of recognizing predictions that should not be trusted and that should activate a healing procedure bringing the DLS to a safe state.&lt;/p&gt; &lt;p&gt;In this paper, we propose an approach to use DNN uncertainty estimators to implement such supervisor.&amp;nbsp;We first discuss advantages and disadvantages of existing approaches to measure uncertainty for DNNs&amp;nbsp;and propose novel metrics for the empirical assessment of the&amp;nbsp; supervisor that rely on such approaches.&amp;nbsp;We then describe our publicly available tool Uncertainty-Wizard, which allows transparent estimation of uncertainty for regular tf.keras DNNs.&amp;nbsp;Lastly, we discuss a large-scale&amp;nbsp; study conducted on four different subjects to empirically validate the approach,&amp;nbsp;reporting the lessons-learned as guidance for software engineers who intend to monitor uncertainty for fail-safe execution of DLS.&lt;/p&gt;</dct:description>
    <dct:accessRights rdf:resource="http://publications.europa.eu/resource/authority/access-right/PUBLIC"/>
    <dct:accessRights>
      <dct:RightsStatement rdf:about="info:eu-repo/semantics/openAccess">
        <rdfs:label>Open Access</rdfs:label>
      </dct:RightsStatement>
    </dct:accessRights>
    <dct:license rdf:resource="https://creativecommons.org/licenses/by/4.0/legalcode"/>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.5055710"/>
        <dcat:byteSize>903143</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/5055710/files/TR-Precrime-2020-05.pdf"/>
        <dcat:mediaType>application/pdf</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
  <foaf:Project rdf:about="info:eu-repo/grantAgreement/EC/H2020/787703/">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">787703</dct:identifier>
    <dct:title>Self-assessment Oracles for Anticipatory Testing</dct:title>
    <frapo:isAwardedBy>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/100010661</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </frapo:isAwardedBy>
  </foaf:Project>
</rdf:RDF>
27
28
views
downloads
All versions This version
Views 2727
Downloads 2828
Data volume 25.3 MB25.3 MB
Unique views 2323
Unique downloads 2525

Share

Cite as