175 citations · 343 across the 24 of their papers we have counts for
9 papers · 1 filter
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…
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…
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.…
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…
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…
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 (…