The generalization performance of deep neural networks comes from their ability to learn, which requires significant computational resources and is extremely energy-intensive, far exceeding the consumption of the brain, from which these models are nevertheless inspired. Neuromorphic architectures approximate the functioning of the brain by connecting as closely as possible to synapses and physical neurons. The use of emerging nano-technologies for these components is very promising to gain density and energy. The training of neural networks is, most often, performed on a circuit external to the network. This externalization of the computations considerably increases the energy cost and the surface area compared to the network alone. To have...
Dans la prochaine ère de l'informatique distribuée, les ordinateurs inspirés par le cerveau qui effe...
Dans cette thèse, nous étudions les applications potentielles des nano-dispositifs mémoires émergent...
By using learning mechanisms extracted from recent discoveries in neuroscience, spiking neural netwo...
The generalization performance of deep neural networks comes from their ability to learn, which requ...
The generalization performance of deep neural networks comes from their ability to learn, which requ...
La performance de généralisation des réseaux de neurones profonds vient de leur capacité d'apprentis...
By 2020, there will be 50 to 100 billion devices connected to the Internet. Two domains of hot resea...
By 2020, there will be 50 to 100 billion devices connected to the Internet. Two domains of hot resea...
By 2020, there will be 50 to 100 billion devices connected to the Internet. Two domains of hot resea...
In this thesis, we study the potential applications of emerging memory nano-devices in computing arc...
Due to the latest evolutions in microelectronic field, a special care has to be given to circuit des...
Due to the latest evolutions in microelectronic field, a special care has to be given to circuit des...
From image recognition to automated driving, machine learning nowadays is all around us and impacts ...
From image recognition to automated driving, machine learning nowadays is all around us and impacts ...
In the next era of distributed computing, brain-based computers that perform operations locally rath...
Dans la prochaine ère de l'informatique distribuée, les ordinateurs inspirés par le cerveau qui effe...
Dans cette thèse, nous étudions les applications potentielles des nano-dispositifs mémoires émergent...
By using learning mechanisms extracted from recent discoveries in neuroscience, spiking neural netwo...
The generalization performance of deep neural networks comes from their ability to learn, which requ...
The generalization performance of deep neural networks comes from their ability to learn, which requ...
La performance de généralisation des réseaux de neurones profonds vient de leur capacité d'apprentis...
By 2020, there will be 50 to 100 billion devices connected to the Internet. Two domains of hot resea...
By 2020, there will be 50 to 100 billion devices connected to the Internet. Two domains of hot resea...
By 2020, there will be 50 to 100 billion devices connected to the Internet. Two domains of hot resea...
In this thesis, we study the potential applications of emerging memory nano-devices in computing arc...
Due to the latest evolutions in microelectronic field, a special care has to be given to circuit des...
Due to the latest evolutions in microelectronic field, a special care has to be given to circuit des...
From image recognition to automated driving, machine learning nowadays is all around us and impacts ...
From image recognition to automated driving, machine learning nowadays is all around us and impacts ...
In the next era of distributed computing, brain-based computers that perform operations locally rath...
Dans la prochaine ère de l'informatique distribuée, les ordinateurs inspirés par le cerveau qui effe...
Dans cette thèse, nous étudions les applications potentielles des nano-dispositifs mémoires émergent...
By using learning mechanisms extracted from recent discoveries in neuroscience, spiking neural netwo...