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

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 ± 0.012. Individual augmentations introduce trade-offs: SCL improves accuracy by 0.28% but reduces clustering (silhouette score 0.637 ± 0.015), while HGRN yields consistent gains in both accuracy (+1.01%) and computational efficiency (170.6×). Full integration achieves a balanced improvement across metrics, reaching a silhouette score of 0.715 ± 0.008, classification accuracy of 97.49 ± 0.10%, energy consumption of 1.85 ± 0.06,μJ, 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.