Metraipolis › archive › dc_1ffa4bcf0763
Low-Latency Activation-Regularized Sparse Neural Operators with Distillation Assistance Towards Real-Time Neuromorphic Virtual Sensing — arXiv:2608.23987
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.23987
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T06:35:44.182Z
- SHA-256 of the archived text
8a88a0cc2acba085d8325e501e6c6de34353f7bb7b93d87d15c6a3a2cc606249- Stable URL of this page
https://metraipolis.com/documento/dc_1ffa4bcf0763
How to cite
Low-Latency Activation-Regularized Sparse Neural Operators with Distillation Assistance Towards Real-Time Neuromorphic Virtual Sensing — arXiv:2608.23987 — arXiv (en), https://arxiv.org/abs/2608.23987 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1ffa4bcf0763 (Metraipolis archive dc_1ffa4bcf0763, sha256 8a88a0cc2acba085d8325e501e6c6de34353f7bb7b93d87d15c6a3a2cc606249)
BibTeX
@misc{dc1ffa4bcf0763,
title = {Low-Latency Activation-Regularized Sparse Neural Operators with Distillation Assistance Towards Real-Time Neuromorphic Virtual Sensing — arXiv:2608.23987},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.23987},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1ffa4bcf0763; sha256 8a88a0cc2acba085d8325e501e6c6de34353f7bb7b93d87d15c6a3a2cc606249},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23987. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Virtual sensing enables digital twins and safety-critical systems to reconstruct and forecast spatial-temporal physics in real time. However, conventional computational and data-driven methods often face challenges in generalization, latency, and energy efficiency for edge deployment. Neural operators offer a promising alternative but remain reliant on power-intensive hardware. Spiking neurons and neuromorphic computing can improve efficiency, yet surrogate-gradient training and multi-step spiking introduce convergence and latency challenges. We propose the Sparse-Activation-ReLU (SAR) layer, a single-step alternative that promotes activation sparsity without surrogate-gradient training while remaining compatible with event-based computing. Within a trunk-based NOMAD architecture, SAR achieves over a fivefold improvement in the combined Latency-Error-Energy (LEE) metric compared with Variable Spiking Neuron (VSN) and Leaky Integrate-and-Fire (LIF) implementations. We further analyze spiking entropy and feature usage and introduce synthetic knowledge distillation, reducing the LEE score by more than twofold. Finally, we improve VSN through a ReLU-based spiking loss and graph-neighbor thresholding. On the Heat Exchanger dataset, these approaches reduce L2 error by more than twofold and nearly sevenfold, respectively, while reducing spiking and spatial aggregation. Overall, the work presented is a step towards energy-efficient virtual sensing by providing an alternative framework that can be positioned towards neuromorphic or other edge device integration that can be a gold standard to compare latency, energy, and error performance for future efficient designs that are sparsity or brain-inspired spiking based. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.23987 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T06:28:52.205Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).