{"ID":2862648,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.26003","arxiv_id":"2509.26003","title":"Scaling Equilibrium Propagation to Deeper Neural Network Architectures","abstract":"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 approach well-suited for implementation on neuromorphic hardware. However, previous studies on equilibrium propagation have been restricted to networks containing only dense layers or relatively small architectures with a few convolutional layers followed by a final dense layer. These networks have a significant gap in accuracy compared to similarly sized feedforward networks trained with backpropagation. In this work, we introduce the Hopfield-Resnet architecture, which incorporates residual (or skip) connections in Hopfield networks with clipped $\\mathrm{ReLU}$ as the activation function. The proposed architectural enhancements enable the training of networks with nearly twice the number of layers reported in prior works. For example, Hopfield-Resnet13 achieves 93.92\\% accuracy on CIFAR-10, which is $\\approx$3.5\\% higher than the previous best result and comparable to that provided by Resnet13 trained using backpropagation.","short_abstract":"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 approach well-suited for implementation on neuromorphic hardware. However, previo...","url_abs":"https://arxiv.org/abs/2509.26003","url_pdf":"https://arxiv.org/pdf/2509.26003v2","authors":"[\"Sankar Vinayak Elayedam\",\"Gopalakrishnan Srinivasan\"]","published":"2025-09-30T09:34:44Z","proceeding":"cs.NE","tasks":"[\"cs.NE\",\"cs.LG\"]","methods":"[]","has_code":false}