| A deep learning framework for neuroscience BA Richards, TP Lillicrap, P Beaudoin, Y Bengio, R Bogacz, ... Nature neuroscience 22 (11), 1761-1770, 2019 | 853 | 2019 |
| Equilibrium propagation: bridging the gap between energy-based models and backpropagation B Scellier, Y Bengio Frontiers in computational neuroscience 11, 24, 2017 | 539 | 2017 |
| Training End-to-End Analog Neural Networks with Equilibrium Propagation J Kendall, R Pantone, K Manickavasagam, Y Bengio, B Scellier arXiv preprint arXiv:2006.01981, 2020 | 91 | 2020 |
| Scaling equilibrium propagation to deep convnets by drastically reducing its gradient estimator bias A Laborieux, M Ernoult, B Scellier, Y Bengio, J Grollier, D Querlioz Frontiers in neuroscience 15, 633674, 2021 | 73 | 2021 |
| Equivalence of equilibrium propagation and recurrent backpropagation B Scellier, Y Bengio Neural computation 31 (2), 312-329, 2019 | 49 | 2019 |
| Generalization of Equilibrium Propagation to Vector Field Dynamics B Scellier, A Goyal, J Binas, T Mesnard, Y Bengio arXiv preprint arXiv:1808.04873, 2018 | 48* | 2018 |
| Updates of equilibrium prop match gradients of backprop through time in an rnn with static input M Ernoult, J Grollier, D Querlioz, Y Bengio, B Scellier Advances in Neural Information Processing Systems 32, 7081-7091, 2019 | 47 | 2019 |
| Equilibrium Propagation with Continual Weight Updates M Ernoult, J Grollier, D Querlioz, Y Bengio, B Scellier arXiv preprint arXiv:2005.04168, 2020 | 41 | 2020 |
| A deep learning theory for neural networks grounded in physics B Scellier arXiv preprint arXiv:2103.09985, 2021 | 22 | 2021 |
| Feedforward initialization for fast inference of deep generative networks is biologically plausible Y Bengio, B Scellier, O Bilaniuk, J Sacramento, W Senn arXiv preprint arXiv:1606.01651, 2016 | 21 | 2016 |
| Learning by non-interfering feedback chemical signaling in physical networks VR Anisetti, B Scellier, JM Schwarz Physical Review Research 5 (2), 023024, 2023 | 16 | 2023 |
| Energy-based learning algorithms for analog computing: a comparative study B Scellier, M Ernoult, J Kendall, S Kumar Advances in Neural Information Processing Systems 36, 2024 | 13* | 2024 |
| Frequency propagation: Multimechanism learning in nonlinear physical networks VR Anisetti, A Kandala, B Scellier, JM Schwarz Neural Computation 36 (4), 596-620, 2024 | 12 | 2024 |
| Agnostic Physics-Driven Deep Learning B Scellier, S Mishra, Y Bengio, Y Ollivier arXiv preprint arXiv:2205.15021, 2022 | 11 | 2022 |
| Vacua of ω-deformed SO (8) supergravity D Berman, T Fischbacher, G Inverso, B Scellier Journal of High Energy Physics 2022 (6), 1-47, 2022 | 6 | 2022 |
| Contrastive learning through non-equilibrium memory M Falk, A Strupp, B Scellier, A Murugan arXiv preprint arXiv:2312.17723, 2023 | 5 | 2023 |
| Quantum Equilibrium Propagation: Gradient-Descent Training of Quantum Systems B Scellier arXiv preprint arXiv:2406.00879, 2024 | 1 | 2024 |
| A universal approximation theorem for nonlinear resistive networks B Scellier, S Mishra arXiv preprint arXiv:2312.15063, 2023 | 1 | 2023 |
| Training of Physical Neural Networks A Momeni, B Rahmani, B Scellier, LG Wright, PL McMahon, CC Wanjura, ... arXiv preprint arXiv:2406.03372, 2024 | | 2024 |
| A Fast Algorithm to Simulate Nonlinear Resistive Networks B Scellier arXiv preprint arXiv:2402.11674, 2024 | | 2024 |
Yoshua BengioProfessor of computer science, University of Montreal, Mila, IVADO, CIFARVerified email at umontreal.ca
