Fetching the paper…
Reading the bibliography…
Energy-based learning algorithms have recently gained a surge of interest due to their compatibility with analog (post-digital) hardware.
Boltzmann machines: Constraint satisfaction networks that learn
G. E. Hinton, T. J. Sejnowski, and D. H. Ackley · 1984
Earlier work this paper cites.
Neurons with graded response have collective computational properties like those of two-state neurons
J. J. Hopfield · 1984
Earlier work this paper cites.
A learning rule for asynchronous perceptrons with feedback in a combinatorial environment
L. B. Almeida · 1987
Earlier work this paper cites.
Generalization of back-propagation to recurrent neural networks
F. J. Pineda · 1987
Earlier work this paper cites.
Contrastive learning and neural oscillations
P. Baldi and F. Pineda · 1991
Earlier work this paper cites.
Contrastive hebbian learning in the continuous hopfield model
J. R. Movellan · 1991
Earlier work this paper cites.
Gradient-based learning applied to document recognition
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner · 1998
Earlier work this paper cites.
Learning multiple layers of features from tiny images
A. Krizhevsky, G. Hinton, et al · 2009
Earlier work this paper cites.
Reading digits in natural images with unsupervised feature learning
Y. Netzer, T. Wang, A. Coates, A. Bissacco, B. Wu, and A. Y. Ng · 2011
Earlier work this paper cites.
Training deep neural networks via direct loss minimization
Y. Song, A. Schwing, R. Urtasun, et al · 2016
Earlier work this paper cites.
Automatic differentiation in pytorch
A. Paszke, S. Gross, S. Chintala, G. Chanan, E. Yang, Z. DeVito, Z. Lin, A. Desmaison, L. Antiga, and A. Lerer · 2017
Earlier work this paper cites.
Equilibrium propagation: Bridging the gap between energy-based models and backpropagation
B. Scellier and Y. Bengio · 2017
Earlier work this paper cites.
Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms
H. Xiao, K. Rasul, and R. Vollgraf · 2017
Earlier work this paper cites.
Implicit generation and modeling with energy based models
Y. Du and I. Mordatch · 2019
Earlier work this paper cites.
Updates of equilibrium prop match gradients of backprop through time in an rnn with static input
M. Ernoult, J. Grollier, D. Querlioz, Y. Bengio, and B. Scellier · 2019
Earlier work this paper cites.
Your classifier is secretly an energy based model and you should treat it like one
W. Grathwohl, K.-C. Wang, J.-H. Jacobsen, D. Duvenaud, M. Norouzi, and K. Swersky · 2019
Earlier work this paper cites.
Learning non-convergent non-persistent short-run mcmc toward energy-based model
E. Nijkamp, M. Hill, S.-C. Zhu, and Y. N. Wu · 2019
Earlier work this paper cites.
Theories of error back-propagation in the brain
J. C. Whittington and R. Bogacz · 2019
Cited alongside, same era.
An image is worth 16x16 words: Transformers for image recognition at scale
A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, et al · 2020
Cited alongside, same era.
Training end-to-end analog neural networks with equilibrium propagation
J. Kendall, R. Pantone, K. Manickavasagam, Y. Bengio, and B. Scellier · 2020
Cited alongside, same era.
Backpropagation and the brain
T. P. Lillicrap, A. Santoro, L. Marris, C. J. Akerman, and G. Hinton · 2020
Cited alongside, same era.
Bounds all around: training energy-based models with bidirectional bounds
C. Geng, J. Wang, Z. Gao, J. Frellsen, and S. Hauberg · 2021
Cited alongside, same era.
Predicting flat-fading channels via meta-learned closed-form linear filters and equilibrium propagation
S. Park and O. Simeone · 2022
Later among the works it cites.
Physical computing for materials acceleration platforms
E. Peterson and A. Lavin · 2022
Later among the works it cites.
Agnostic physics-driven deep learning
B. Scellier, S. Mishra, Y. Bengio, and Y. Ollivier · 2022
Later among the works it cites.
Physical learning beyond the quasistatic limit
M. Stern, S. Dillavou, M. Z. Miskin, D. J. Durian, and A. J. Liu · 2022
Later among the works it cites.
Desynchronous learning in a physics-driven learning network
J. Wycoff, S. Dillavou, M. Stern, A. Liu, and D. Durian · 2022
Later among the works it cites.
Beyond backpropagation: bilevel optimization through implicit differentiation and equilibrium propagation
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
J. Kendall · 2021
Cited alongside, same era.
Scaling equilibrium propagation to deep convnets by drastically reducing its gradient estimator bias
A. Laborieux, M. Ernoult, B. Scellier, Y. Bengio, J. Grollier, and D. Querlioz · 2021
Cited alongside, same era.
Training dynamical binary neural networks with equilibrium propagation
J. Laydevant, M. Ernoult, D. Querlioz, and J. Grollier · 2021
Cited alongside, same era.
A deep learning theory for neural networks grounded in physics
B. Scellier · 2021
Cited alongside, same era.
Supervised learning in physical networks: From machine learning to learning machines
M. Stern, D. Hexner, J. W. Rocks, and A. J. Liu · 2021
Cited alongside, same era.
Frequency propagation: Multi-mechanism learning in nonlinear physical networks
V. R. Anisetti, A. Kandala, B. Scellier, and J. Schwarz · 2022
Cited alongside, same era.
Demonstration of decentralized physics-driven learning
S. Dillavou, M. Stern, A. J. Liu, and D. J. Durian · 2022
Cited alongside, same era.
N. Zucchet and J. Sacramento · 2022
Later among the works it cites.
A contrastive rule for meta-learning
N. Zucchet, S. Schug, J. Von Oswald, D. Zhao, and J. Sacramento · 2022
Later among the works it cites.
Learning by non-interfering feedback chemical signaling in physical networks
V. R. Anisetti, B. Scellier, and J. M. Schwarz · 2023
Closest in time.
Circuits that train themselves: decentralized, physics-driven learning
S. Dillavou, B. Beyer, M. Stern, M. Z. Miskin, A. J. Liu, and D. J. Durian · 2023
Closest in time.
Training precise stress patterns
D. Hexner · 2023
Closest in time.
Dual propagation: Accelerating contrastive hebbian learning with dyadic neurons
R. Høier, D. Staudt, and C. Zach · 2023
Closest in time.
Training an ising machine with equilibrium propagation
J. Laydevant, D. Markovic, and J. Grollier · 2023
Closest in time.
Learning without neurons in physical systems
M. Stern and A. Murugan · 2023
Closest in time.
Physical learning of power-efficient solutions
M. Stern, S. Dillavou, D. Jayaraman, D. J. Durian, and A. J. Liu · 2023
Closest in time.
Energy-based analog neural network framework
M. Watfa, A. Garcia-Ortiz, and G. Sassatelli · 2023
Closest in time.
Activity-difference training of deep neural networks using memristor crossbars
S.-i. Yi, J. D. Kendall, R. S. Williams, and S. Kumar · 2023
Closest in time.