Memory-Augmented Spiking Networks: Synergistic Integration of Complementary Mechanisms for Neuromorphic Vision

TL;DR

This paper explores combining various memory mechanisms in spiking neural networks to enhance neuromorphic vision, demonstrating that balanced integration improves accuracy, efficiency, and neuronal organization.

Contribution

It systematically investigates the integration of multiple memory augmentation strategies in SNNs, revealing optimal combinations for improved performance and efficiency.

Findings

Full integration improves accuracy to 97.49%.

HGRN enhances efficiency by 170.6×.

Structured neuronal assemblies are maintained with integration.

Abstract

Spiking Neural Networks (SNNs) provide biological plausibility and energy efficiency, yet systematic investigations of memory augmentation strategies remain limited. We conduct a five-model ablation study integrating Leaky Integrate-and-Fire neurons, Supervised Contrastive Learning (SCL), Hopfield networks, and Hierarchical Gated Recurrent Networks (HGRN) on the N-MNIST dataset. Baseline SNNs exhibit organized neuronal groupings, or structured assemblies, characterized by a silhouette score of $0.687 \pm 0.012$. Individual augmentations introduce trade-offs: SCL improves accuracy by $0.28\%$ but reduces clustering (silhouette score $0.637 \pm 0.015$), while HGRN yields consistent gains in both accuracy ($+1.01\%$) and computational efficiency ($170.6\times$). Full integration achieves a balanced improvement across metrics, reaching a silhouette score of $0.715 \pm 0.008$, classification accuracy of $97.49 \pm 0.10\%$, energy consumption of $1.85 \pm 0.06\,\mu\mathrm{J}$, and sparsity of $97.0\%$. These results indicate that optimal performance emerges from architectural balance rather than isolated optimization, establishing design principles for memory-augmented neuromorphic systems.