Modality-Dependent Memory Mechanisms in Cross-Modal Neuromorphic Computing
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911329636319232 |
|---|---|
| author | Blessing, Effiong Tseng, Chiung-Yi Roy, Somshubhra Rehman, Junaid Nkrumah, Isaac |
| author_facet | Blessing, Effiong Tseng, Chiung-Yi Roy, Somshubhra Rehman, Junaid Nkrumah, Isaac |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_18575 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Modality-Dependent Memory Mechanisms in Cross-Modal Neuromorphic Computing Blessing, Effiong Tseng, Chiung-Yi Roy, Somshubhra Rehman, Junaid Nkrumah, Isaac Machine Learning Artificial Intelligence Neural and Evolutionary Computing 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. |
| title | Modality-Dependent Memory Mechanisms in Cross-Modal Neuromorphic Computing |
| topic | Machine Learning Artificial Intelligence Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2512.18575 |