Modalitydependent Memory Mechanisms In Crossmodal Neuromorphic Computing

# Modality-Dependent Memory Mechanisms in Cross-Modal Neuromorphic Computing

**arXiv ID:** 2512.18575
**Authors:** Effiong Blessing, Chiung-Yi Tseng, Somshubhra Roy, Junaid Rehman, Isaac Nkrumah
**Published:** 2025-12-21T03:18:42Z
**Abstract:**
Memory-augmented spiking neural networks (SNNs) promise energy-efficient neuromorphic computing, yet their generalization across sensory modalities remains unexplored. We present the first comprehensive cross-modal ablation study of memory mechanisms in SNNs, evaluating Hopfield networks, Hierarchical Gated Recurrent Networks (HGRNs), and supervised contrastive learning (SCL) across visual (N-MNIST) and auditory (SHD) neuromorphic datasets. Our systematic evaluation of five architectures reveals striking modality-dependent performance patterns: Hopfield networks achieve 97.68% accuracy on visual tasks but only 76.15% on auditory tasks (21.53 point gap), revealing severe modality-specific specialization, while SCL demonstrates more balanced cross-modal performance (96.72% visual, 82.16% audio, 14.56 point gap). These findings establish that memory mechanisms exhibit task-specific benefits rather than universal applicability. Joint multi-modal training with HGRN achieves 94.41% visual and 79.37% audio accuracy (88.78% average), matching parallel HGRN performance through unified deployment. Quantitative engram analysis confirms weak cross-modal alignment (0.038 similarity), validating our parallel architecture design. Our work provides the first empirical evidence for modality-specific memory optimization in neuromorphic systems, achieving 603x energy efficiency over traditional neural networks.

## Skill Description

This skill is generated from the arXiv paper: Modality-Dependent Memory Mechanisms in Cross-Modal Neuromorphic Computing (2512.18575).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2512.18575](http://arxiv.org/abs/2512.18575v1)