SOURCE-LINKED INTELLIGENCE

Towards an Expressivity-Normalized Energy-Demand Comparison of ANNs and SNNs

arXiv · AI, language, vision and robotics · article · Aug 30, 2026 · UTC

Spiking neural networks (SNNs) are often regarded as energy-efficient alternatives to artificial neural networks (ANNs), yet their advantage depends critically on both network architecture and data properties. We develop an analytical framework to compare fully-connected ReLU ANNs and integrate-and-fire SNNs for time-series data with respect to their theoretical energy efficiency at matched expressive capacity. By relating an inference-energy model to theoretical bounds on representational expressivity, we derive an expressivity-normalized efficiency ratio and explicit thresholds in network wi

Read original source ↗ Open in workspace

recordType

paper

region

Global