<?xml version="1.0" encoding="UTF-8"?><mets:mets xmlns:mads="http://www.loc.gov/mads/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:tef="http://www.abes.fr/abes/documents/tef" xmlns:metsRights="http://cosimo.stanford.edu/sdr/metsrights/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:dcterms="http://purl.org/dc/terms/" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mets="http://www.loc.gov/METS/">
    <mets:metsHdr ID="rennes1-ori-wf-1-19268" CREATEDATE="2024-03-14T17:52:05" LASTMODDATE="2024-03-14T17:52:05">
  <mets:agent ROLE="CREATOR">
            <mets:name>Université de Rennes</mets:name>
        </mets:agent>
</mets:metsHdr>
    <mets:dmdSec ID="desc_expr" CREATED="2024-03-14T17:52:05">
  <mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_desc_these">
            <mets:xmlData>
                <tef:thesisRecord>
     <dc:title xml:lang="en">Reliability of Deep Learning with rare event simulation : theory and practice</dc:title>
     <dcterms:alternative xml:lang="fr">Fiabilité du Deep Learning avec simulation d’événements rares : théorie et pratique</dcterms:alternative>
     <dc:subject xml:lang="fr">simulation d'événements rares</dc:subject><dc:subject xml:lang="fr">ingénierie statistique de fiabilité</dc:subject><dc:subject xml:lang="fr">apprentissage profond</dc:subject>
     <dc:subject xml:lang="en">rare event simulation</dc:subject><dc:subject xml:lang="en">statistical reliability engineering</dc:subject><dc:subject xml:lang="en">deep learning</dc:subject><tef:sujetRameau><tef:vedetteRameauNomCommun>
						<tef:elementdEntree autoriteSource="Sudoc" autoriteExterne="030971098">Réseaux neuronaux (informatique)</tef:elementdEntree>
					</tef:vedetteRameauNomCommun><tef:vedetteRameauNomCommun>
						<tef:elementdEntree autoriteSource="Sudoc" autoriteExterne="223540633">Apprentissage profond</tef:elementdEntree>
					</tef:vedetteRameauNomCommun></tef:sujetRameau>
     <dcterms:abstract xml:lang="fr">Cette thèse étudie la fiabilité des réseaux de neurones profonds en utilisant des algorithmes de simulation d’événements rares dans le cadre de l’ingénierie de la fiabilité statistique. L’objectif est d’évaluer et d’améliorer la robustesse de ces réseaux dans des situations peu communes mais cruciales. La recherche se concentre sur le développement de nouvelles méthodes statistiques spécifiquement pour les réseaux de neurones profonds. Ces méthodes sont conçues pour mieux comprendre comment ces réseaux se comportent face à des données inhabituelles ou corrompues. Une réalisation clé est la création d’un nouvel algorithme qui améliore l’applicabilité des techniques d’échantillonnage d’importance aux classificateurs différentiables, une caractéristique commune dans les modèles modernes d’apprentissage profond. L’étude met en évidence les difficultés d’application des méthodes traditionnelles de fiabilité statistique aux données complexes et de grande dimension typiques en apprentissage profond. Malgré ces défis, les résultats offrent des outils et des approches qui peuvent être appliqués à divers modèles d’apprentissage profond.</dcterms:abstract>
     <dcterms:abstract xml:lang="en">This thesis investigates the reliability of deep neural networks using rare event simulation algorithms within the framework of statistical reliability engineering. The goal is to assess and improve the robustness of these networks in situations that are not commonly encountered but are critical. The research focuses on developing new statistical methods specifically for deep neural networks. These methods are designed to better understand how these networks behave when faced with unusual or corrupted data. A key achievement is the creation of a new algorithm that improves the applicability of importance sampling techniques to classifiers that are differentiable, a common trait in modern Deep Learning models. The study highlights the difficulties of applying traditional statistical reliability methods to the complex and high-dimensional data typical in Deep Learning. Despite these challenges, the findings offer valuable tools and approaches that can be applied to various deep-learning models.</dcterms:abstract>
     <dc:type>Electronic Thesis or Dissertation</dc:type><dc:type xsi:type="dcterms:DCMIType">Text</dc:type>
     <dc:language xsi:type="dcterms:RFC3066">en</dc:language>
    </tef:thesisRecord>
            </mets:xmlData>
        </mets:mdWrap>
</mets:dmdSec>
    <mets:dmdSec ID="desc_edition" CREATED="2024-03-14T17:52:05">
  <mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_desc_edition">
            <mets:xmlData>
                <tef:edition><dcterms:medium xsi:type="dcterms:IMT">application/pdf</dcterms:medium><dcterms:extent>1 : 8639 Ko</dcterms:extent><dc:identifier xsi:type="dcterms:URI">https://ged.univ-rennes1.fr/nuxeo/site/esupversions/28781ebb-ab23-4340-8d0a-2c7eac61b04e</dc:identifier></tef:edition>
            </mets:xmlData>
        </mets:mdWrap>
</mets:dmdSec>
    <mets:amdSec>
        <mets:techMD ID="admin_expr">
            <mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_admin_these">
                <mets:xmlData>
                    <tef:thesisAdmin>
                        <tef:auteur>
       <tef:nom>Tit</tef:nom>
       <tef:prenom>Karim</tef:prenom>
       
       <tef:dateNaissance>1996-06-09</tef:dateNaissance>
       <tef:nationalite scheme="ISO-3166-1">FR</tef:nationalite>
       <tef:autoriteExterne autoriteSource="Sudoc">280816499</tef:autoriteExterne>
       <tef:autoriteExterne autoriteSource="mailPerso">titkarim@gmail.com</tef:autoriteExterne>
      </tef:auteur>
                        <dc:identifier xsi:type="tef:NNT">2024URENS024</dc:identifier>
                        <dc:identifier xsi:type="tef:nationalThesisPID">http://www.theses.fr/2024URENS024</dc:identifier>
                        <dcterms:dateAccepted xsi:type="dcterms:W3CDTF">2024-04-22</dcterms:dateAccepted>
                        <tef:thesis.degree>
                            <tef:thesis.degree.discipline xml:lang="fr">Informatique</tef:thesis.degree.discipline>
                            <tef:thesis.degree.grantor>
        <tef:nom>Université de Rennes</tef:nom><tef:autoriteInterne>thesis.degree.grantor_1</tef:autoriteInterne>
        
        <tef:autoriteExterne autoriteSource="Sudoc">26693823X</tef:autoriteExterne>
       </tef:thesis.degree.grantor>
                            <tef:thesis.degree.level>Doctorat</tef:thesis.degree.level>
                        </tef:thesis.degree>
                        <tef:theseSurTravaux>non</tef:theseSurTravaux>
                        <tef:avisJury>oui</tef:avisJury><tef:directeurThese><tef:nom>Furon</tef:nom><tef:prenom>Teddy</tef:prenom><tef:autoriteInterne>intervenant_1</tef:autoriteInterne><tef:autoriteExterne autoriteSource="Sudoc">078044758</tef:autoriteExterne></tef:directeurThese><tef:directeurThese><tef:nom>Rousset</tef:nom><tef:prenom>Mathias</tef:prenom><tef:autoriteInterne>intervenant_2</tef:autoriteInterne><tef:autoriteExterne autoriteSource="Sudoc">115320857</tef:autoriteExterne></tef:directeurThese><tef:presidentJury><tef:nom>Tuffin</tef:nom><tef:prenom>Bruno</tef:prenom><tef:autoriteInterne>intervenant_3</tef:autoriteInterne><tef:autoriteExterne autoriteSource="Sudoc">115631143</tef:autoriteExterne></tef:presidentJury><tef:membreJury><tef:nom>Furon</tef:nom><tef:prenom>Teddy</tef:prenom><tef:autoriteInterne>intervenant_1</tef:autoriteInterne><tef:autoriteExterne autoriteSource="Sudoc">078044758</tef:autoriteExterne></tef:membreJury><tef:membreJury><tef:nom>Rousset</tef:nom><tef:prenom>Mathias</tef:prenom><tef:autoriteInterne>intervenant_2</tef:autoriteInterne><tef:autoriteExterne autoriteSource="Sudoc">115320857</tef:autoriteExterne></tef:membreJury><tef:membreJury><tef:nom>Gerchinovitz</tef:nom><tef:prenom>Sébastien</tef:prenom><tef:autoriteInterne>intervenant_5</tef:autoriteInterne><tef:autoriteExterne autoriteSource="Sudoc">156515776</tef:autoriteExterne></tef:membreJury><tef:membreJury><tef:nom>Guyader</tef:nom><tef:prenom>Arnaud</tef:prenom><tef:autoriteInterne>intervenant_6</tef:autoriteInterne><tef:autoriteExterne autoriteSource="Sudoc">061067342</tef:autoriteExterne></tef:membreJury><tef:membreJury><tef:nom>Lagnoux</tef:nom><tef:prenom>Agnès</tef:prenom><tef:autoriteInterne>intervenant_7</tef:autoriteInterne><tef:autoriteExterne autoriteSource="Sudoc">115081461</tef:autoriteExterne></tef:membreJury><tef:rapporteur><tef:nom>Morio</tef:nom><tef:prenom>Jérôme</tef:prenom><tef:autoriteInterne>intervenant_4</tef:autoriteInterne><tef:autoriteExterne autoriteSource="Sudoc">128195320</tef:autoriteExterne></tef:rapporteur><tef:rapporteur><tef:nom>Bourinet</tef:nom><tef:prenom>Jean-Marc</tef:prenom><tef:autoriteInterne>intervenant_8</tef:autoriteInterne><tef:autoriteExterne autoriteSource="Sudoc">160358817</tef:autoriteExterne></tef:rapporteur>
      
      
                        
                        
                        <tef:ecoleDoctorale>
       <tef:nom>MATISSE</tef:nom><tef:autoriteInterne>ecoleDoctorale_1</tef:autoriteInterne>
       
       <tef:autoriteExterne autoriteSource="Sudoc">267602553</tef:autoriteExterne>
      </tef:ecoleDoctorale>
                        <tef:partenaireRecherche type="laboratoire">
       <tef:nom>
IRISA
</tef:nom><tef:autoriteInterne>partenaireRecherche_1</tef:autoriteInterne>
       
       <tef:autoriteExterne autoriteSource="Sudoc">
026386909
</tef:autoriteExterne>
      </tef:partenaireRecherche>
                        <tef:oaiSetSpec>ddc:004</tef:oaiSetSpec>
                        
                        
                        
                    <tef:MADSAuthority authorityID="intervenant_1" type="personal"><tef:personMADS><mads:namePart type="family">Furon</mads:namePart><mads:namePart type="given">Teddy</mads:namePart></tef:personMADS></tef:MADSAuthority><tef:MADSAuthority authorityID="intervenant_2" type="personal"><tef:personMADS><mads:namePart type="family">Rousset</mads:namePart><mads:namePart type="given">Mathias</mads:namePart></tef:personMADS></tef:MADSAuthority><tef:MADSAuthority authorityID="intervenant_3" type="personal"><tef:personMADS><mads:namePart type="family">Tuffin</mads:namePart><mads:namePart type="given">Bruno</mads:namePart></tef:personMADS></tef:MADSAuthority><tef:MADSAuthority authorityID="intervenant_4" type="personal"><tef:personMADS><mads:namePart type="family">Morio</mads:namePart><mads:namePart type="given">Jérôme</mads:namePart></tef:personMADS></tef:MADSAuthority><tef:MADSAuthority authorityID="intervenant_5" type="personal"><tef:personMADS><mads:namePart type="family">Gerchinovitz</mads:namePart><mads:namePart type="given">Sébastien</mads:namePart></tef:personMADS></tef:MADSAuthority><tef:MADSAuthority authorityID="intervenant_6" type="personal"><tef:personMADS><mads:namePart type="family">Guyader</mads:namePart><mads:namePart type="given">Arnaud</mads:namePart></tef:personMADS></tef:MADSAuthority><tef:MADSAuthority authorityID="intervenant_7" type="personal"><tef:personMADS><mads:namePart type="family">Lagnoux</mads:namePart><mads:namePart type="given">Agnès</mads:namePart></tef:personMADS></tef:MADSAuthority><tef:MADSAuthority authorityID="intervenant_8" type="personal"><tef:personMADS><mads:namePart type="family">Bourinet</mads:namePart><mads:namePart type="given">Jean-Marc</mads:namePart></tef:personMADS></tef:MADSAuthority><tef:MADSAuthority authorityID="thesis.degree.grantor_1" type="corporate"><tef:personMADS><mads:namePart>Université de Rennes</mads:namePart></tef:personMADS></tef:MADSAuthority><tef:MADSAuthority authorityID="ecoleDoctorale_1" type="corporate"><tef:personMADS><mads:namePart>MATISSE</mads:namePart></tef:personMADS></tef:MADSAuthority><tef:MADSAuthority authorityID="partenaireRecherche_1" type="corporate"><tef:personMADS><mads:namePart>
IRISA
</mads:namePart></tef:personMADS></tef:MADSAuthority></tef:thesisAdmin>
                </mets:xmlData>
            </mets:mdWrap>
        </mets:techMD><mets:techMD ID="file_1"><mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_tech_fichier"><mets:xmlData><tef:meta_fichier>
     <tef:encodage>ASCII</tef:encodage>
     <tef:formatFichier>PDF</tef:formatFichier>
     
     
     
     <tef:taille>8846548</tef:taille>
    </tef:meta_fichier></mets:xmlData></mets:mdWrap></mets:techMD>
        
        <mets:rightsMD ID="dr_expr_thesard">
            <mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_droits_auteur_these">
                <mets:xmlData>
                    <metsRights:RightsDeclarationMD>
                        <metsRights:Context CONTEXTCLASS="GENERAL PUBLIC">
                            <metsRights:Permissions DISCOVER="true" DISPLAY="true" COPY="true" DUPLICATE="true" MODIFY="false" DELETE="false" PRINT="true"/>
                        </metsRights:Context>
                    </metsRights:RightsDeclarationMD>
                </mets:xmlData>
            </mets:mdWrap>
        </mets:rightsMD>
        <mets:rightsMD ID="dr_expr_univ">
            <mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_droits_etablissement_these">
                <mets:xmlData>
                    <metsRights:RightsDeclarationMD>
                        <metsRights:Context CONTEXTCLASS="GENERAL PUBLIC">
                            <metsRights:Permissions DISCOVER="true" DISPLAY="true" COPY="true" DUPLICATE="true" MODIFY="false" DELETE="false" PRINT="true"/>
                        </metsRights:Context>
                    </metsRights:RightsDeclarationMD>
                </mets:xmlData>
            </mets:mdWrap>
        </mets:rightsMD>
        <mets:rightsMD ID="dr_version">
            <mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_droits_version">
                <mets:xmlData>
                    <metsRights:RightsDeclarationMD>
                        <metsRights:Context CONTEXTCLASS="GENERAL PUBLIC">
                            <metsRights:Permissions DISCOVER="true" DISPLAY="true" COPY="true" DUPLICATE="true" MODIFY="false" DELETE="false" PRINT="true"/>
                        </metsRights:Context>
                    </metsRights:RightsDeclarationMD>
                </mets:xmlData>
            </mets:mdWrap>
        </mets:rightsMD>
    </mets:amdSec>
    <mets:fileSec>
  <mets:fileGrp ID="FGrID1" USE="archive"><mets:file ID="FID1" ADMID="file_1" MIMETYPE="application/pdf" USE="maitre"><mets:FLocat LOCTYPE="URL" xlink:href="https://ged.univ-rennes1.fr/nuxeo/site/esupversions/28781ebb-ab23-4340-8d0a-2c7eac61b04e"/></mets:file></mets:fileGrp>
 </mets:fileSec>
    <mets:structMap TYPE="logical">
        <mets:div DMDID="desc_expr" ADMID="dr_expr_thesard dr_expr_univ admin_expr" TYPE="THESE" CONTENTIDS="http://ori-oai-search.univ-rennes1.fr/uid/rennes1-ori-wf-1-19268/oeuvre">
            <mets:div ADMID="dr_version" TYPE="VERSION_COMPLETE" CONTENTIDS="http://ori-oai-search.univ-rennes1.fr/uid/rennes1-ori-wf-1-19268/oeuvre/version">
                <mets:div DMDID="desc_edition" TYPE="EDITION" CONTENTIDS="http://ori-oai-search.univ-rennes1.fr/uid/rennes1-ori-wf-1-19268/oeuvre/version/edition">
                    <mets:fptr FILEID="FGrID1"/>
                </mets:div>
            </mets:div>
        </mets:div>
    </mets:structMap>
</mets:mets>