Fetching the paper…

Reading the bibliography…

2017

Equivalence of Equilibrium Propagation and Recurrent Backpropagation

Scellier, Benjamin, Bengio, Yoshua

Original
PDF
Post on X

Understand

Recurrent Backpropagation and Equilibrium Propagation are supervised learning algorithms for fixed point recurrent neural networks which differ in their second phase.

In the first phase, both algorithms converge to a fixed point which corresponds to the configuration where the prediction is made.
In the second phase, Equilibrium Propagation relaxes to another nearby fixed point corresponding to smaller prediction error, whereas Recurrent Backpropagation uses a side network to compute error derivatives iteratively.
In this work we establish a close connection between these two algorithms.

Equivalence of Equilibrium Propagation and Recurrent Backpropagation · Around

Built on

Absolute stability of global pattern formation and parallel memory storage by competitive neural networks
M. A. Cohen and S. Grossberg · 1983
Earlier work this paper cites.
Neurons with graded responses 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.

Similar

Generalization of back-propagation to recurrent neural networks
F. J. Pineda · 1987
Cited alongside, same era.
Learning representations by recirculation
G. E. Hinton and J. L. McClelland · 1988
Cited alongside, same era.
A theoretical framework for back-propagation
Y. LeCun, D. Touresky, G. Hinton, and T. Sejnowski · 1988
Cited alongside, same era.

Then

The recent excitement about neural networks
F. Crick · 1989
Later among the works it cites.
Equilibrium propagation: Bridging the gap between energy-based models and backpropagation
Original
B. Scellier and Y. Bengio · 2017
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…