Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Benjamin Scellier

A deep learning theory for neural networks grounded in physics


Mar 18, 2021
Benjamin Scellier


  Access Paper or Ask Questions

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


Jan 14, 2021
Axel Laborieux, Maxence Ernoult, Benjamin Scellier, Yoshua Bengio, Julie Grollier, Damien Querlioz

* NeurIPS 2020 Workshop : "Beyond Backpropagation Novel Ideas for Training Neural Architectures". arXiv admin note: substantial text overlap with arXiv:2006.03824 

  Access Paper or Ask Questions

Training End-to-End Analog Neural Networks with Equilibrium Propagation


Jun 09, 2020
Jack Kendall, Ross Pantone, Kalpana Manickavasagam, Yoshua Bengio, Benjamin Scellier


  Access Paper or Ask Questions

Equilibrium Propagation with Continual Weight Updates


Apr 29, 2020
Maxence Ernoult, Julie Grollier, Damien Querlioz, Yoshua Bengio, Benjamin Scellier


  Access Paper or Ask Questions

Continual Weight Updates and Convolutional Architectures for Equilibrium Propagation


Apr 29, 2020
Maxence Ernoult, Julie Grollier, Damien Querlioz, Yoshua Bengio, Benjamin Scellier


  Access Paper or Ask Questions

Updates of Equilibrium Prop Match Gradients of Backprop Through Time in an RNN with Static Input


May 31, 2019
Maxence Ernoult, Julie Grollier, Damien Querlioz, Yoshua Bengio, Benjamin Scellier


  Access Paper or Ask Questions

Generalization of Equilibrium Propagation to Vector Field Dynamics


Aug 14, 2018
Benjamin Scellier, Anirudh Goyal, Jonathan Binas, Thomas Mesnard, Yoshua Bengio


  Access Paper or Ask Questions

Equivalence of Equilibrium Propagation and Recurrent Backpropagation


May 22, 2018
Benjamin Scellier, Yoshua Bengio


  Access Paper or Ask Questions

Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation


Mar 28, 2017
Benjamin Scellier, Yoshua Bengio


  Access Paper or Ask Questions

Feedforward Initialization for Fast Inference of Deep Generative Networks is biologically plausible


Jun 28, 2016
Yoshua Bengio, Benjamin Scellier, Olexa Bilaniuk, Joao Sacramento, Walter Senn


  Access Paper or Ask Questions