Dependence of Equilibrium Propagation Training Success on Network Architecture

2026-01-29

AI Summary

This study addresses the connectivity constraints and high energy consumption inherent in hardware implementations of conventional dense neural networks by presenting the first systematic evaluation of Equilibrium Propagation (EP) on physically realizable sparse, locally connected architectures—such as those inspired by XY spin lattice models. By training locally connected networks on standard benchmark tasks and integrating dynamic analyses of spatial coupling and response evolution, the work elucidates how network topology influences training efficacy. The results demonstrate that sparsely connected architectures with only local connectivity can achieve performance comparable to fully connected networks, thereby offering a practical and scalable design pathway for energy-efficient neuromorphic hardware.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Hardware-aware ML
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

The rapid rise of artificial intelligence has led to an unsustainable growth in energy consumption. This has motivated progress in neuromorphic computing and physics-based training of learning machines as alternatives to digital neural networks. Many theoretical studies focus on simple architectures like all-to-all or densely connected layered networks. However, these may be challenging to realize experimentally, e.g. due to connectivity constraints. In this work, we investigate the performance of the widespread physics-based training method of equilibrium propagation for more realistic architectural choices, specifically, locally connected lattices. We train an XY model and explore the influence of architecture on various benchmark tasks, tracking the evolution of spatially distributed responses and couplings during training. Our results show that sparse networks with only local connections can achieve performance comparable to dense networks. Our findings provide guidelines for further scaling up architectures based on equilibrium propagation in realistic settings.

Problem

• equilibrium propagation
• network architecture
• locally connected
• neuromorphic computing
• physics-based training

Innovation

• Equilibrium Propagation
• Locally Connected Architecture
• Neuromorphic Computing
• Sparse Networks
• Physics-based Training