User profiles for Timothée Masquelier
Timothée MasquelierCNRS Researcher (DR2), Cerco (CNRS-UT3), TMBI (Univ. Toulouse) Verified email at cnrs.fr Cited by 7917 |
[HTML][HTML] Unsupervised learning of visual features through spike timing dependent plasticity
T Masquelier, SJ Thorpe - PLoS computational biology, 2007 - journals.plos.org
Spike timing dependent plasticity (STDP) is a learning rule that modifies synaptic strength
as a function of the relative timing of pre- and postsynaptic spikes. When a neuron is …
as a function of the relative timing of pre- and postsynaptic spikes. When a neuron is …
Deep learning in spiking neural networks
…, M Ghodrati, SR Kheradpisheh, T Masquelier… - Neural networks, 2019 - Elsevier
In recent years, deep learning has revolutionized the field of machine learning, for computer
vision in particular. In this approach, a deep (multilayer) artificial neural network (ANN) is …
vision in particular. In this approach, a deep (multilayer) artificial neural network (ANN) is …
STDP-based spiking deep convolutional neural networks for object recognition
Previous studies have shown that spike-timing-dependent plasticity (STDP) can be used in
spiking neural networks (SNN) to extract visual features of low or intermediate complexity in …
spiking neural networks (SNN) to extract visual features of low or intermediate complexity in …
Hardware implementation of convolutional STDP for on-line visual feature learning
A Yousefzadeh, T Masquelier… - … on circuits and …, 2017 - ieeexplore.ieee.org
We present a highly hardware friendly STDP (Spike Timing Dependent Plasticity) learning
rule for training Spiking Convolutional Cores in Unsupervised mode and training Fully …
rule for training Spiking Convolutional Cores in Unsupervised mode and training Fully …
Incorporating learnable membrane time constant to enhance learning of spiking neural networks
Spiking Neural Networks (SNNs) have attracted enormous research interest due to temporal
information processing capability, low power consumption, and high biological plausibility. …
information processing capability, low power consumption, and high biological plausibility. …
Deep residual learning in spiking neural networks
Deep Spiking Neural Networks (SNNs) present optimization difficulties for gradient-based
approaches due to discrete binary activation and complex spatial-temporal dynamics. …
approaches due to discrete binary activation and complex spatial-temporal dynamics. …
[HTML][HTML] On spike-timing-dependent-plasticity, memristive devices, and building a self-learning visual cortex
…, JA Pérez-Carrasco, T Masquelier… - Frontiers in …, 2011 - frontiersin.org
In this paper we present a very exciting overlap between emergent nanotechnology and
neuroscience, which has been discovered by neuromorphic engineers. Specifically, we are …
neuroscience, which has been discovered by neuromorphic engineers. Specifically, we are …
[HTML][HTML] STDP and STDP variations with memristors for spiking neuromorphic learning systems
T Serrano-Gotarredona, T Masquelier… - Frontiers in …, 2013 - frontiersin.org
In this paper we review several ways of realizing asynchronous Spike-Timing-Dependent-Plasticity
(STDP) using memristors as synapses. Our focus is on how to use individual …
(STDP) using memristors as synapses. Our focus is on how to use individual …
SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence
Spiking neural networks (SNNs) aim to realize brain-inspired intelligence on neuromorphic
chips with high energy efficiency by introducing neural dynamics and spike properties. As the …
chips with high energy efficiency by introducing neural dynamics and spike properties. As the …
Competitive STDP-based spike pattern learning
T Masquelier, R Guyonneau, SJ Thorpe - Neural computation, 2009 - direct.mit.edu
Recently it has been shown that a repeating arbitrary spatiotemporal spike pattern hidden in
equally dense distracter spike trains can be robustly detected and learned by a single …
equally dense distracter spike trains can be robustly detected and learned by a single …