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...
We propose a method for autonomous agent navigation problem grounded on a connectionist architecture...
We introduce a novel system of interconnected Self- Organizing Maps that can be used to build feedfo...
We propose a method for autonomous agent navigation problem grounded on a connectionist architecture...
This thesis focuses on unifying multiple modal data flows that may be provided by sensors of an agen...
Cette thèse traite de la problématique de l'unification de différents flux d'informations modales qu...
International audienceIn the field of computational neuroscience, we develop distributed models of t...
International audienceSOMMA (Self Organizing Maps for Multimodal Association) consists on cortically...
International audiencePresentation of the SOMMA model in the CogSys 2012 conferencePrésentation du m...
International audiencePresentation of the SOMMA model in the CogSys 2012 conferencePrésentation du m...
The field of computational neurosciences is interested in modeling the cognitive functions through b...
To move in a complex and changing environment, according to the active perception theory, an agent n...
The field of computational neurosciences is interested in modeling the cognitive functions through b...
The cerebral cortex appears in many models as an architecture of autonomous modules connected retroa...
Texte intégral accessible uniquement aux membres de l'Université de LorraineThis thesis aims at sett...
This thesis aims at setting up a sensory-motor loop, that can be usedin robotics, while using biolog...
We propose a method for autonomous agent navigation problem grounded on a connectionist architecture...
We introduce a novel system of interconnected Self- Organizing Maps that can be used to build feedfo...
We propose a method for autonomous agent navigation problem grounded on a connectionist architecture...
This thesis focuses on unifying multiple modal data flows that may be provided by sensors of an agen...
Cette thèse traite de la problématique de l'unification de différents flux d'informations modales qu...
International audienceIn the field of computational neuroscience, we develop distributed models of t...
International audienceSOMMA (Self Organizing Maps for Multimodal Association) consists on cortically...
International audiencePresentation of the SOMMA model in the CogSys 2012 conferencePrésentation du m...
International audiencePresentation of the SOMMA model in the CogSys 2012 conferencePrésentation du m...
The field of computational neurosciences is interested in modeling the cognitive functions through b...
To move in a complex and changing environment, according to the active perception theory, an agent n...
The field of computational neurosciences is interested in modeling the cognitive functions through b...
The cerebral cortex appears in many models as an architecture of autonomous modules connected retroa...
Texte intégral accessible uniquement aux membres de l'Université de LorraineThis thesis aims at sett...
This thesis aims at setting up a sensory-motor loop, that can be usedin robotics, while using biolog...
We propose a method for autonomous agent navigation problem grounded on a connectionist architecture...
We introduce a novel system of interconnected Self- Organizing Maps that can be used to build feedfo...
We propose a method for autonomous agent navigation problem grounded on a connectionist architecture...