Thomas Mesquida
YOU?
Author Swipe
View article: Scaling-up Memristor Monte Carlo with magnetic domain-wall physics
Scaling-up Memristor Monte Carlo with magnetic domain-wall physics Open
By exploiting the intrinsic random nature of nanoscale devices, Memristor Monte Carlo (MMC) is a promising enabler of edge learning systems. However, due to multiple algorithmic and device-level limitations, existing demonstrations have be…
View article: Improving the Robustness of Neural Networks to Noisy Multi-Level Non-Volatile Memory-based Synapses
Improving the Robustness of Neural Networks to Noisy Multi-Level Non-Volatile Memory-based Synapses Open
International audience
View article: Leveraging Sparsity with Spiking Recurrent Neural Networks for Energy-Efficient Keyword Spotting
Leveraging Sparsity with Spiking Recurrent Neural Networks for Energy-Efficient Keyword Spotting Open
International audience
View article: Backpropagation-Based Learning Techniques for Deep Spiking Neural Networks: A Survey
Backpropagation-Based Learning Techniques for Deep Spiking Neural Networks: A Survey Open
With the adoption of smart systems, artificial neural networks (ANNs) have become ubiquitous. Conventional ANN implementations have high energy consumption, limiting their use in embedded and mobile applications. Spiking neural networks (S…
View article: Spike-based Beamforming using pMUT Arrays for Ultra-Low Power Gesture Recognition
Spike-based Beamforming using pMUT Arrays for Ultra-Low Power Gesture Recognition Open
International audience
View article: Are SNNs Really More Energy-Efficient Than ANNs? an In-Depth Hardware-Aware Study
Are SNNs Really More Energy-Efficient Than ANNs? an In-Depth Hardware-Aware Study Open
International audience
View article: SpikiLi: A Spiking Simulation of LiDAR based Real-time Object Detection for Autonomous Driving
SpikiLi: A Spiking Simulation of LiDAR based Real-time Object Detection for Autonomous Driving Open
Spiking Neural Networks are a recent and new neural network design approach that promises tremendous improvements in power efficiency, computation efficiency, and processing latency. They do so by using asynchronous spike-based data flow, …
View article: Neuromorphic object localization using resistivememories and ultrasonic transducers
Neuromorphic object localization using resistivememories and ultrasonic transducers Open
Real-world sensory-processing applications require compact, low-latency, and low-power computing systems. Enabled by their in-memory event-driven computing abilities, hybrid memristive-CMOS neuromorphic architectures provide an ideal hardw…
View article: Fully-Integrated Spiking Neural Network Using SiO<sub>x</sub>-Based RRAM as Synaptic Device
Fully-Integrated Spiking Neural Network Using SiO<sub>x</sub>-Based RRAM as Synaptic Device Open
International audience