activity
20162022
most citedLow-Energy Truly Random Number Generation with Superparamagnetic Tunnel Junctions for Unconventional Computing

175 citations · 343 across the 24 of their papers we have counts for

collaborators
Showing cs.NEShow all

9 papers · 1 filter

cs.NE2021

Training Dynamical Binary Neural Networks with Equilibrium Propagation

Jérémie Laydevant, Maxence Ernoult, Damien Querlioz +1

Equilibrium Propagation (EP) is an algorithm intrinsically adapted to the training of physical networks, thanks to the local updates of weights given by the internal dynamics of th…

cs.NE2021

Synaptic metaplasticity in binarized neural networks

Axel Laborieux, Maxence Ernoult, Tifenn Hirtzlin +1

Unlike the brain, artificial neural networks, including state-of-the-art deep neural networks for computer vision, are subject to "catastrophic forgetting": they rapidly forget the…

cs.NE2020

EqSpike: Spike-driven Equilibrium Propagation for Neuromorphic Implementations

Erwann Martin, Maxence Ernoult, Jérémie Laydevant +4

Finding spike-based learning algorithms that can be implemented within the local constraints of neuromorphic systems, while achieving high accuracy, remains a formidable challenge.…

cs.NE2020

Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing its Gradient Estimator Bias

Axel Laborieux, Maxence Ernoult, Benjamin Scellier +3

Equilibrium Propagation (EP) is a biologically-inspired algorithm for convergent RNNs with a local learning rule that comes with strong theoretical guarantees. The parameter update…

cs.NE2020

Continual Weight Updates and Convolutional Architectures for Equilibrium Propagation

Maxence Ernoult, Julie Grollier, Damien Querlioz +2

Equilibrium Propagation (EP) is a biologically inspired alternative algorithm to backpropagation (BP) for training neural networks. It applies to RNNs fed by a static input x that…

cs.NE202017 cited

Equilibrium Propagation with Continual Weight Updates

Maxence Ernoult, Julie Grollier, Damien Querlioz +2

Equilibrium Propagation (EP) is a learning algorithm that bridges Machine Learning and Neuroscience, by computing gradients closely matching those of Backpropagation Through Time (…