English
Related papers

Related papers: Equilibrium Propagation for Dissipative Dynamics

200 papers

Equilibrium Propagation (EP) is a physics-inspired learning algorithm that uses stationary states of a dynamical system both for inference and learning. In its original formulation it is limited to conservative systems, $\textit{i.e.}$ to…

Machine Learning · Computer Science 2026-02-04 Antonino Emanuele Scurria , Dimitri Vanden Abeele , Bortolo Matteo Mognetti , Serge Massar

Machine learning is a powerful method of extracting meaning from data; unfortunately, current digital hardware is extremely energy-intensive. There is interest in an alternative analog computing implementation that could match the…

Machine Learning · Computer Science 2026-02-17 Jonathan Lin , Aman Desai , Frank Barrows , Francesco Caravelli

We propose a method for training dynamical systems governed by Lagrangian mechanics using Equilibrium Propagation. Our approach extends Equilibrium Propagation - initially developed for energy-based models - to dynamical trajectories by…

Chaotic Dynamics · Physics 2025-07-21 Serge Massar

Equilibrium propagation (EP) is a training framework for energy-based systems, i.e. systems whose physics minimizes an energy function. EP has been explored in various classical physical systems such as resistor networks, elastic networks,…

Quantum Physics · Physics 2024-06-04 Benjamin Scellier

We introduce Equilibrium Propagation, a learning framework for energy-based models. It involves only one kind of neural computation, performed in both the first phase (when the prediction is made) and the second phase of training (after the…

Machine Learning · Computer Science 2017-03-30 Benjamin Scellier , Yoshua Bengio

Equilibrium propagation is a recently introduced method to use and train artificial neural networks in which the network is at the minimum (more generally extremum) of an energy functional. Equilibrium propagation has shown good performance…

Quantum Physics · Physics 2024-12-03 Serge Massar , Bortolo Matteo Mognetti

Equilibrium propagation (EP) is an alternative to backpropagation (BP) that allows the training of deep neural networks with local learning rules. It thus provides a compelling framework for training neuromorphic systems and understanding…

Machine Learning · Computer Science 2022-09-02 Axel Laborieux , Friedemann Zenke

Backpropagation learning algorithm, the workhorse of modern artificial intelligence, is notoriously difficult to implement in physical neural networks. Equilibrium Propagation (EP) is an alternative with comparable efficiency and strong…

Machine Learning · Computer Science 2026-03-17 Karol Sajnok , Michał Matuszewski

Oscillator networks represent a promising technology for unconventional computing and artificial intelligence. Thus far, these systems have primarily been demonstrated in small-scale implementations, such as Ising Machines for solving…

Disordered Systems and Neural Networks · Physics 2025-04-17 Théophile Rageau , Julie Grollier

Equilibrium Propagation (EP) is a biologically inspired local learning rule first proposed for convergent recurrent neural networks (CRNNs), in which synaptic updates depend only on neuron states from two distinct phases. EP estimates…

Machine Learning · Computer Science 2026-05-11 Jiaqi Lin , Malyaban Bal , Abhronil Sengupta

This work establishes that a physical system can perform statistical learning without gradient computations, via an Agnostic Equilibrium Propagation (Aeqprop) procedure that combines energy minimization, homeostatic control, and nudging…

Machine Learning · Computer Science 2022-05-31 Benjamin Scellier , Siddhartha Mishra , Yoshua Bengio , Yann Ollivier

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…

Machine Learning · Computer Science 2018-05-24 Benjamin Scellier , Yoshua Bengio

Equilibrium propagation has been proposed as a biologically plausible alternative to the backpropagation algorithm. The local nature of gradient computations, combined with the use of convergent RNNs to reach equilibrium states, make this…

Neural and Evolutionary Computing · Computer Science 2026-03-19 Sankar Vinayak Elayedam , Gopalakrishnan Srinivasan

The widespread adoption of machine learning and artificial intelligence in all branches of science and technology has created a need for energy-efficient, alternative hardware platforms. While such neuromorphic approaches have been proposed…

Quantum Physics · Physics 2024-06-11 Clara C. Wanjura , Florian Marquardt

The reverse process in score-based diffusion models is formally equivalent to overdamped Langevin dynamics in a time-dependent energy landscape. In our prior work we showed that a bilinearly-coupled analog substrate can physically realize…

Machine Learning · Computer Science 2026-04-28 Aditi De

Computing the loss gradient via backpropagation consumes considerable energy during deep learning (DL) model training. In this paper, we propose a novel approach to efficiently compute DL models' gradients to mitigate the substantial energy…

Computer Vision and Pattern Recognition · Computer Science 2024-06-12 Challapalli Phanindra Revanth , Sumohana S. Channappayya , C Krishna Mohan

Equilibrium Propagation (EP) is a supervised learning algorithm that trains network parameters using local neuronal activity. This is in stark contrast to backpropagation, where updating the parameters of the network requires significant…

Machine Learning · Computer Science 2025-04-01 Jonathan Peters , Philippe Talatchian

Equilibrium Propagation (EP) is a learning algorithm that bridges Machine Learning and Neuroscience, by computing gradients closely matching those of Backpropagation Through Time (BPTT), but with a learning rule local in space. Given an…

Neural and Evolutionary Computing · Computer Science 2020-05-11 Maxence Ernoult , Julie Grollier , Damien Querlioz , Yoshua Bengio , Benjamin Scellier

We introduce a principled method to train end-to-end analog neural networks by stochastic gradient descent. In these analog neural networks, the weights to be adjusted are implemented by the conductances of programmable resistive devices…

Neural and Evolutionary Computing · Computer Science 2020-06-11 Jack Kendall , Ross Pantone , Kalpana Manickavasagam , Yoshua Bengio , Benjamin Scellier

Self-assembly, the process by which interacting components form well-defined and often intricate structures, is typically thought of as a spontaneous process arising from equilibrium dynamics. When a system is driven by external…

Statistical Mechanics · Physics 2021-11-12 Shriram Chennakesavalu , Grant M. Rotskoff
‹ Prev 1 2 3 10 Next ›