MIRAMOND , Benoît

Les réseaux de neurones connaissent aujourd'hui un engouement sans précédent grâce à l'explosion de l'open data et de la puissance de calcul toujours plus importante des ordinateurs actuels. Cependant, diverses applications telles que la reconnaissance de la voix ou la détection et classification d'objets nécessitent une implémentation...

Self-organization is a powerful bio-inspired feature that has been poorly investigated in the context of hardware computing architectures. The neural foundations of brain selforganization enable structural plasticity, continuous learning,and tolerance to lesions but at the cost of massive lateralsynaptic connections. A cellular formulation of...

Automotive embedded algorithms have very high constraints in terms of latency, accuracy and power consumption. In this work, we propose to train spiking neural networks (SNNs) directly on data coming from event cameras to design fast and efficient automotive embedded applications. Indeed, SNNs are more biologically realistic neural networks...

We present in this paper a predictive analysis method based on a unsupervised type of machine learning algorithm : the kohonenmaps. This model will be exploited in a network of sensors to reduce the number of transmission on the network. The aim of thispaper is to present a learning algorithm and the result obtained in the context of smart city.

Spiking neural networks are considered as the third generation of Artificial Neural Networks. SNNs perform computation using neurons and synapses that communicate using binary and asynchronous signals known as spikes. They have attracted significant research interest over the last years since their computing paradigm allows theoretically sparse...

Le développement des objets connectés et de l'internet des objets (IoT) ouvre la voie à de nombreuses applications notamment dans l'accumulation et le traitement de grand volume de donnée (Big Data) via par exemple les réseaux de capteurs sans fils. Ceux-ci sont un ensemble de senseurs capable de surveiller leur environnement et de connecter,...

In this paper, we present SPLEAT, a SPiking Low-power Event-based ArchiTecture for the hardware deployment of Spiking Neural Networks (SNN). SPLEAT is designed as a configurable architecture that allows integrating several hardware modules representing different neural layers and, therefore, gives the ability to deploy a wide range of deep...

Ce travail aborde le problème de la classification d'objets à partir de leurs signatures électromagnétiques en utilisant des réseaux de neurones convolutifs (ou CNN pour Convolutional Neural Network). La classification porte à la fois sur la forme, le matériau et l'orientation spatiale de l'objet dans un repère défini par la position des...

An increasing demand on the autonomy of mobile robotic platforms requires adaptive on-line decisions reacting to the dynamic and unpredictable working environment with respect to the robotic mission requirements. These decisions are constrained by the limited computing resources and the energy that the mobile robot can carry. Moreover, in a...