Spatial learning of multimodal correlations in a cortically inspired way
Identifieur interne : 004674 ( Hal/Corpus ); précédent : 004673; suivant : 004675Spatial learning of multimodal correlations in a cortically inspired way
Auteurs : Mathieu LefortSource :
Descripteurs français
English descriptors
Abstract
This thesis focuses on unifying multiple modal data flows that may be provided by sensors of an agent. This unification, inspired by psychological experiments like the ventriloquist effect, is based on detecting correlations which are defined as temporally recurrent spatial patterns that appear in the input flows. Learning of the input flow correlations space consists on sampling this space and generalizing these learned samples. This thesis proposed some functional paradigms for multimodal data processing, leading to the connectionist, generic, modular and cortically inspired architecture SOMMA (Self-Organizing Maps for Multimodal Association). In this model, each modal stimulus is processed in a cortical map. Interconnection of these maps provides an unifying multimodal data processing. Sampling and generalization of correlations are based on the constrained self-organization of each map. The model is characterised by a gradual emergence of these functional properties: monomodal properties lead to the emergence of multimodal ones and learning of correlations in each map precedes self-organization of these maps. Furthermore, the use of a connectionist architecture and of on-line and unsupervised learning provides plasticity and robustness properties to the data processing in SOMMA. Classical artificial intelligence models usually miss such properties.
Url:
Links to Exploration step
Hal:tel-00756687Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Spatial learning of multimodal correlations in a cortically inspired way</title>
<title xml:lang="fr">Apprentissage spatial de corrélations multimodales par des mécanismes d'inspiration corticale</title>
<author><name sortKey="Lefort, Mathieu" sort="Lefort, Mathieu" uniqKey="Lefort M" first="Mathieu" last="Lefort">Mathieu Lefort</name>
<affiliation><hal:affiliation type="researchteam" xml:id="struct-205107" status="OLD"><idno type="RNSR">200018289J</idno>
<orgName>Neuromimetic intelligence</orgName>
<orgName type="acronym">CORTEX</orgName>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/equipes/cortex</ref>
</desc>
<listRelation><relation active="#struct-129671" type="direct"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-423090" type="direct"></relation>
<relation active="#struct-206040" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
<tutelles><tutelle active="#struct-129671" type="direct"><org type="laboratory" xml:id="struct-129671" status="VALID"><idno type="RNSR">198618246Y</idno>
<orgName>INRIA Nancy - Grand Est</orgName>
<desc><address><addrLine>615 rue du Jardin Botanique 54600 Villers-lès-Nancy</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/nancy</ref>
</desc>
<listRelation><relation active="#struct-300009" type="direct"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-300009" type="indirect"><org type="institution" xml:id="struct-300009" status="VALID"><orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
<orgName type="acronym">Inria</orgName>
<desc><address><addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/en/</ref>
</desc>
</org>
</tutelle>
<tutelle active="#struct-423090" type="direct"><org type="department" xml:id="struct-423090" status="VALID"><orgName>Department of Complex Systems, Artificial Intelligence & Robotics</orgName>
<orgName type="acronym">LORIA - AIS</orgName>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr/la-recherche-en/departements/complex-system-and-artificial-intelligence</ref>
</desc>
<listRelation><relation active="#struct-206040" type="direct"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-206040" type="indirect"><org type="laboratory" xml:id="struct-206040" status="VALID"><idno type="IdRef">067077927</idno>
<idno type="RNSR">198912571S</idno>
<idno type="IdUnivLorraine">[UL]RSI--</idno>
<orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
<orgName type="acronym">LORIA</orgName>
<date type="start">2012-01-01</date>
<desc><address><addrLine>Campus Scientifique BP 239 54506 Vandoeuvre-lès-Nancy Cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr</ref>
</desc>
<listRelation><relation active="#struct-300009" type="direct"></relation>
<relation active="#struct-413289" type="direct"></relation>
<relation name="UMR7503" active="#struct-441569" type="direct"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-413289" type="indirect"><org type="institution" xml:id="struct-413289" status="VALID"><idno type="IdRef">157040569</idno>
<idno type="IdUnivLorraine">[UL]100--</idno>
<orgName>Université de Lorraine</orgName>
<orgName type="acronym">UL</orgName>
<date type="start">2012-01-01</date>
<desc><address><addrLine>34 cours Léopold - CS 25233 - 54052 Nancy cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.univ-lorraine.fr/</ref>
</desc>
</org>
</tutelle>
<tutelle name="UMR7503" active="#struct-441569" type="indirect"><org type="institution" xml:id="struct-441569" status="VALID"><idno type="IdRef">02636817X</idno>
<idno type="ISNI">0000000122597504</idno>
<orgName>Centre National de la Recherche Scientifique</orgName>
<orgName type="acronym">CNRS</orgName>
<date type="start">1939-10-19</date>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.cnrs.fr/</ref>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">HAL</idno>
<idno type="RBID">Hal:tel-00756687</idno>
<idno type="halId">tel-00756687</idno>
<idno type="halUri">https://tel.archives-ouvertes.fr/tel-00756687</idno>
<idno type="url">https://tel.archives-ouvertes.fr/tel-00756687</idno>
<date when="2012-07-04">2012-07-04</date>
<idno type="wicri:Area/Hal/Corpus">004674</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Spatial learning of multimodal correlations in a cortically inspired way</title>
<title xml:lang="fr">Apprentissage spatial de corrélations multimodales par des mécanismes d'inspiration corticale</title>
<author><name sortKey="Lefort, Mathieu" sort="Lefort, Mathieu" uniqKey="Lefort M" first="Mathieu" last="Lefort">Mathieu Lefort</name>
<affiliation><hal:affiliation type="researchteam" xml:id="struct-205107" status="OLD"><idno type="RNSR">200018289J</idno>
<orgName>Neuromimetic intelligence</orgName>
<orgName type="acronym">CORTEX</orgName>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/equipes/cortex</ref>
</desc>
<listRelation><relation active="#struct-129671" type="direct"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-423090" type="direct"></relation>
<relation active="#struct-206040" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
<tutelles><tutelle active="#struct-129671" type="direct"><org type="laboratory" xml:id="struct-129671" status="VALID"><idno type="RNSR">198618246Y</idno>
<orgName>INRIA Nancy - Grand Est</orgName>
<desc><address><addrLine>615 rue du Jardin Botanique 54600 Villers-lès-Nancy</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/nancy</ref>
</desc>
<listRelation><relation active="#struct-300009" type="direct"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-300009" type="indirect"><org type="institution" xml:id="struct-300009" status="VALID"><orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
<orgName type="acronym">Inria</orgName>
<desc><address><addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/en/</ref>
</desc>
</org>
</tutelle>
<tutelle active="#struct-423090" type="direct"><org type="department" xml:id="struct-423090" status="VALID"><orgName>Department of Complex Systems, Artificial Intelligence & Robotics</orgName>
<orgName type="acronym">LORIA - AIS</orgName>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr/la-recherche-en/departements/complex-system-and-artificial-intelligence</ref>
</desc>
<listRelation><relation active="#struct-206040" type="direct"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-206040" type="indirect"><org type="laboratory" xml:id="struct-206040" status="VALID"><idno type="IdRef">067077927</idno>
<idno type="RNSR">198912571S</idno>
<idno type="IdUnivLorraine">[UL]RSI--</idno>
<orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
<orgName type="acronym">LORIA</orgName>
<date type="start">2012-01-01</date>
<desc><address><addrLine>Campus Scientifique BP 239 54506 Vandoeuvre-lès-Nancy Cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr</ref>
</desc>
<listRelation><relation active="#struct-300009" type="direct"></relation>
<relation active="#struct-413289" type="direct"></relation>
<relation name="UMR7503" active="#struct-441569" type="direct"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-413289" type="indirect"><org type="institution" xml:id="struct-413289" status="VALID"><idno type="IdRef">157040569</idno>
<idno type="IdUnivLorraine">[UL]100--</idno>
<orgName>Université de Lorraine</orgName>
<orgName type="acronym">UL</orgName>
<date type="start">2012-01-01</date>
<desc><address><addrLine>34 cours Léopold - CS 25233 - 54052 Nancy cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.univ-lorraine.fr/</ref>
</desc>
</org>
</tutelle>
<tutelle name="UMR7503" active="#struct-441569" type="indirect"><org type="institution" xml:id="struct-441569" status="VALID"><idno type="IdRef">02636817X</idno>
<idno type="ISNI">0000000122597504</idno>
<orgName>Centre National de la Recherche Scientifique</orgName>
<orgName type="acronym">CNRS</orgName>
<date type="start">1939-10-19</date>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.cnrs.fr/</ref>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
</affiliation>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="mix" xml:lang="en"><term>multimodal integration</term>
<term>neural networks</term>
<term>on-line and unsupervised learning</term>
<term>self-organization</term>
</keywords>
<keywords scheme="mix" xml:lang="fr"><term>apprentissage continu et non supervisé</term>
<term>auto-organisation</term>
<term>multimodalité</term>
<term>réseau de neurones</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">This thesis focuses on unifying multiple modal data flows that may be provided by sensors of an agent. This unification, inspired by psychological experiments like the ventriloquist effect, is based on detecting correlations which are defined as temporally recurrent spatial patterns that appear in the input flows. Learning of the input flow correlations space consists on sampling this space and generalizing these learned samples. This thesis proposed some functional paradigms for multimodal data processing, leading to the connectionist, generic, modular and cortically inspired architecture SOMMA (Self-Organizing Maps for Multimodal Association). In this model, each modal stimulus is processed in a cortical map. Interconnection of these maps provides an unifying multimodal data processing. Sampling and generalization of correlations are based on the constrained self-organization of each map. The model is characterised by a gradual emergence of these functional properties: monomodal properties lead to the emergence of multimodal ones and learning of correlations in each map precedes self-organization of these maps. Furthermore, the use of a connectionist architecture and of on-line and unsupervised learning provides plasticity and robustness properties to the data processing in SOMMA. Classical artificial intelligence models usually miss such properties.</div>
</front>
</TEI>
<hal api="V3"><titleStmt><title xml:lang="en">Spatial learning of multimodal correlations in a cortically inspired way</title>
<title xml:lang="fr">Apprentissage spatial de corrélations multimodales par des mécanismes d'inspiration corticale</title>
<author role="aut"><persName><forename type="first">Mathieu</forename>
<surname>Lefort</surname>
</persName>
<email>mathieu.lefort@loria.fr</email>
<ptr type="url" target="http://www.loria.fr/~lefortma"></ptr>
<idno type="idhal">mathieu-lefort</idno>
<idno type="halauthor">701629</idno>
<affiliation ref="#struct-205107"></affiliation>
</author>
<editor role="depositor"><persName><forename>Mathieu</forename>
<surname>Lefort</surname>
</persName>
<email>mathieu.lefort@liris.cnrs.fr</email>
</editor>
</titleStmt>
<editionStmt><edition n="v1" type="current"><date type="whenSubmitted">2012-11-23 14:59:59</date>
<date type="whenModified">2015-09-22 01:12:24</date>
<date type="whenReleased">2012-11-26 14:47:25</date>
<date type="whenProduced">2012-07-04</date>
<date type="whenEndEmbargoed">2012-11-23</date>
<ref type="file" target="https://tel.archives-ouvertes.fr/tel-00756687/document"><date notBefore="2012-11-23"></date>
</ref>
<ref type="file" n="1" target="https://tel.archives-ouvertes.fr/tel-00756687/file/manuscrit.pdf"><date notBefore="2012-11-23"></date>
</ref>
</edition>
<respStmt><resp>contributor</resp>
<name key="142280"><persName><forename>Mathieu</forename>
<surname>Lefort</surname>
</persName>
<email>mathieu.lefort@liris.cnrs.fr</email>
</name>
</respStmt>
</editionStmt>
<publicationStmt><distributor>CCSD</distributor>
<idno type="halId">tel-00756687</idno>
<idno type="halUri">https://tel.archives-ouvertes.fr/tel-00756687</idno>
<idno type="halBibtex">lefort:tel-00756687</idno>
<idno type="halRefHtml">Réseau de neurones [cs.NE]. Université Nancy II, 2012. Français</idno>
<idno type="halRef">Réseau de neurones [cs.NE]. Université Nancy II, 2012. Français</idno>
</publicationStmt>
<seriesStmt><idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
<idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
<idno type="stamp" n="INRIA-LORRAINE">INRIA Nancy - Grand Est</idno>
<idno type="stamp" n="LORIA2">Publications du LORIA</idno>
<idno type="stamp" n="INRIA-NANCY-GRAND-EST">INRIA Nancy - Grand Est</idno>
<idno type="stamp" n="LORIA">LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications</idno>
<idno type="stamp" n="LORIA-CSAI" p="LORIA">Systèmes complexes et intelligence artificielle</idno>
<idno type="stamp" n="UNIV-LORRAINE">Université de Lorraine</idno>
<idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
</seriesStmt>
<notesStmt></notesStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Spatial learning of multimodal correlations in a cortically inspired way</title>
<title xml:lang="fr">Apprentissage spatial de corrélations multimodales par des mécanismes d'inspiration corticale</title>
<author role="aut"><persName><forename type="first">Mathieu</forename>
<surname>Lefort</surname>
</persName>
<email>mathieu.lefort@loria.fr</email>
<ptr type="url" target="http://www.loria.fr/~lefortma"></ptr>
<idno type="idHal">mathieu-lefort</idno>
<idno type="halAuthorId">701629</idno>
<affiliation ref="#struct-205107"></affiliation>
</author>
</analytic>
<monogr><imprint><date type="dateDefended">2012-07-04</date>
</imprint>
<authority type="institution">Université Nancy II</authority>
<authority type="supervisor">Bernard Girau(bernard.girau@loria.fr)</authority>
<authority type="jury">Jean-Christophe Buisson (président)</authority>
<authority type="jury">Hugues Berry (rapporteur)</authority>
<authority type="jury">Arnaud Revel (rapporteur)</authority>
<authority type="jury">Yann Boniface (examinateur)</authority>
<authority type="jury">Benoît Girard (examinateur)</authority>
</monogr>
</biblStruct>
</sourceDesc>
<profileDesc><langUsage><language ident="fr">French</language>
</langUsage>
<textClass><keywords scheme="author"><term xml:lang="en">multimodal integration</term>
<term xml:lang="en">self-organization</term>
<term xml:lang="en">neural networks</term>
<term xml:lang="en">on-line and unsupervised learning</term>
<term xml:lang="fr">multimodalité</term>
<term xml:lang="fr">auto-organisation</term>
<term xml:lang="fr">réseau de neurones</term>
<term xml:lang="fr">apprentissage continu et non supervisé</term>
</keywords>
<classCode scheme="halDomain" n="info.info-ne">Computer Science [cs]/Neural and Evolutionary Computing [cs.NE]</classCode>
<classCode scheme="halDomain" n="info.info-lg">Computer Science [cs]/Machine Learning [cs.LG]</classCode>
<classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</classCode>
<classCode scheme="halTypology" n="THESE">Theses</classCode>
</textClass>
<abstract xml:lang="en">This thesis focuses on unifying multiple modal data flows that may be provided by sensors of an agent. This unification, inspired by psychological experiments like the ventriloquist effect, is based on detecting correlations which are defined as temporally recurrent spatial patterns that appear in the input flows. Learning of the input flow correlations space consists on sampling this space and generalizing these learned samples. This thesis proposed some functional paradigms for multimodal data processing, leading to the connectionist, generic, modular and cortically inspired architecture SOMMA (Self-Organizing Maps for Multimodal Association). In this model, each modal stimulus is processed in a cortical map. Interconnection of these maps provides an unifying multimodal data processing. Sampling and generalization of correlations are based on the constrained self-organization of each map. The model is characterised by a gradual emergence of these functional properties: monomodal properties lead to the emergence of multimodal ones and learning of correlations in each map precedes self-organization of these maps. Furthermore, the use of a connectionist architecture and of on-line and unsupervised learning provides plasticity and robustness properties to the data processing in SOMMA. Classical artificial intelligence models usually miss such properties.</abstract>
<abstract xml:lang="fr">Cette thèse traite de la problématique de l'unification de différents flux d'informations modales qui peuvent provenir des senseurs d'un agent. Cette unification, inspirée des expériences psychologiques comme l'effet ventriloque, s'appuie sur la détection de corrélations, définies comme des motifs spatiaux qui apparaissent régulièrement dans les flux d'entrée. L'apprentissage de l'espace des corrélations du flux d'entrée échantillonne cet espace et généralise les échantillons appris. Cette thèse propose des principes fonctionnels pour le traitement multimodal de l'information qui ont aboutit à l'architecture connexionniste, générique, modulaire et cortico-inspirée SOMMA (Self-Organizing Maps for Multimodal Association). Dans ce modèle, le traitement de chaque modalité s'effectue au sein d'une carte corticale. L'unification multimodale de l'information est obtenue par la mise en relation réciproque de ces cartes. L'échantillonnage et la généralisation des corrélations reposent sur une auto-organisation contrainte des cartes. Ce modèle est caractérisé par un apprentissage progressif de ces propriétés fonctionnelles: les propriétés monomodales amorcent l'émergence des propriétés multimodales et, dans le même temps, l'apprentissage de certaines corrélations par chaque carte est un préalable à l'auto-organisation de ces cartes. Par ailleurs, l'utilisation d'une architecture connexionniste et d'un apprentissage continu et non supervisé fournit au modèle des propriétés de robustesse et d'adaptabilité qui sont généralement absentes des approches informatiques classiques.</abstract>
</profileDesc>
</hal>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Hal/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 004674 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Hal/Corpus/biblio.hfd -nk 004674 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Lorraine |area= InforLorV4 |flux= Hal |étape= Corpus |type= RBID |clé= Hal:tel-00756687 |texte= Spatial learning of multimodal correlations in a cortically inspired way }}
![]() | This area was generated with Dilib version V0.6.33. | ![]() |