Since a few years, neural networks analysis rouses great interests. According to this approach, the study of postulated functions in the nervous system demands some powerful simulation tools . Taking inspiration from general features of signais processing and front present tendances toward parallelism in computer architecture, we propose an efficient array processor architecture for recursive adoptive networks analysis and more generally for data (signal, image) analysis : it's the processor named CRAS Y (a systolique calculator for adaptive networks) .Depuis de nombreuses années, l'analyse de réseaux neuronaux suit un essor fantastique . L'étude suivant cette approche des fonctions postulées dans le système nerveux requiert de puissan...
The new submicronic technologies offer real capacities in terms of integration of signal processing ...
Research in the field of neuromorphic- and cognitive- computing has generated a lot of interest in r...
The most significant drawback in using neighbourhood processing (linear filtering, morphology) is th...
Les réseaux de neurones profonds ont permis des progrès sans précédent dans le domaine del’apprentis...
Pattern recognition is a fundamental task for living beings and is perform very efficiently by the b...
Artificial intelligence is a field that, historically, has benefited from the combination of ideas f...
Nowadays, Artificial Intelligence (AI) is a widespread concept applied to many fields such as transp...
The problem of sources discrimination, very classical in Signal Processing field, is also an actual ...
Les algorithmes d’apprentissage profond permettent aux ordinateurs de réaliser des tâches cognitives...
In this paper, we propose a complete system of analysis of images, which includes the whole sequenc...
National audienceResearch advances in the field of neurobiology imply that neural networks are becom...
This thesis studies empirical properties of deep convolutional neural networks, and in particular th...
Studying how our nervous system and sensory mechanisms work lead to the creation of event-driven sen...
Computer vision is an interdisciplinary field that investigates how computers can gain a high level ...
Our study tries to combine scattered results in image processing, artificial intelligence, psycholo...
The new submicronic technologies offer real capacities in terms of integration of signal processing ...
Research in the field of neuromorphic- and cognitive- computing has generated a lot of interest in r...
The most significant drawback in using neighbourhood processing (linear filtering, morphology) is th...
Les réseaux de neurones profonds ont permis des progrès sans précédent dans le domaine del’apprentis...
Pattern recognition is a fundamental task for living beings and is perform very efficiently by the b...
Artificial intelligence is a field that, historically, has benefited from the combination of ideas f...
Nowadays, Artificial Intelligence (AI) is a widespread concept applied to many fields such as transp...
The problem of sources discrimination, very classical in Signal Processing field, is also an actual ...
Les algorithmes d’apprentissage profond permettent aux ordinateurs de réaliser des tâches cognitives...
In this paper, we propose a complete system of analysis of images, which includes the whole sequenc...
National audienceResearch advances in the field of neurobiology imply that neural networks are becom...
This thesis studies empirical properties of deep convolutional neural networks, and in particular th...
Studying how our nervous system and sensory mechanisms work lead to the creation of event-driven sen...
Computer vision is an interdisciplinary field that investigates how computers can gain a high level ...
Our study tries to combine scattered results in image processing, artificial intelligence, psycholo...
The new submicronic technologies offer real capacities in terms of integration of signal processing ...
Research in the field of neuromorphic- and cognitive- computing has generated a lot of interest in r...
The most significant drawback in using neighbourhood processing (linear filtering, morphology) is th...