Introduces Ising-dynamics-inspired equilibrium propagation with extended phase-space dynamics to lower energy barriers and train deep convolutional Hopfield networks on MNIST, FashionMNIST, and CIFAR-10 at backpropagation-comparable accuracy.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A VGG10 predictive coding network is trained on ImageNet via equilibrium propagation to 13.23% top-5 error, close to the 12.2% backpropagation baseline, marking the first such demonstration at this scale.
citing papers explorer
-
Hybridizing Equilibrium Propagation with Ising Machines for Efficient Energy-Based Learning
Introduces Ising-dynamics-inspired equilibrium propagation with extended phase-space dynamics to lower energy barriers and train deep convolutional Hopfield networks on MNIST, FashionMNIST, and CIFAR-10 at backpropagation-comparable accuracy.
-
Training a Predictive Coding Network on ImageNet using Equilibrium Propagation
A VGG10 predictive coding network is trained on ImageNet via equilibrium propagation to 13.23% top-5 error, close to the 12.2% backpropagation baseline, marking the first such demonstration at this scale.