•  
  •  
 

Author ORCID Identifier

https://orcid.org/0009-0007-0066-9918

Abstract

We propose an extension of renormalization into the domain of spiking neural networks, thereby providing a novel framework for coarse-graining neural networks without disrupting their critical properties. The proposed coarse-graining technique merges neurons and synaptic connections based on a graph-theoretic distance derived from synaptic weight strength and is configured to effectively prune the reservoir size while preserving the scale-free spiking dynamics indicative of criticality. Criticality in spiking neural networks may provide information-theoretic advantages by optimizing information processing and sensitivity to input. Using time-series prediction benchmarks, we demonstrate that networks operating at criticality exhibit up to 32% higher prediction accuracy before coarse-graining and up to 30% higher prediction accuracy after coarse-graining when compared to non critical networks for a sufficiently complex task.

Share

COinS