Saved in:
Bibliographic Details
Main Authors: Song, Zihang, Popovski, Petar
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.08490
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915627042603008
author Song, Zihang
Popovski, Petar
author_facet Song, Zihang
Popovski, Petar
contents We present a neuromorphic split-computing framework for energy-efficient low-latency inference over optical inter-satellite links. The system partitions a spiking neural network (SNN) between edge and core nodes. To transmit sparse spiking features efficiently, we introduce a lossless channel-block-sparse event representation that exploits inter- and intra-channel sparsity. We employ hierarchical error protection using multi-level forward error correction and cyclic redundancy checks to ensure reliable communication without retransmission. The framework uses end-to-end training with sparsity and clustering regularizers, combined with channel-aware stochastic masking to optimize feature compression and channel robustness jointly. In a proof-of-concept implementation on remote sensing imagery, the framework achieves over $10 \times$ reduction in both computational energy and transmission load compared to conventional dense split systems, with less than 1% accuracy loss. The proposed approach also outperforms address-event-based split SNNs by $3.7 \times$ in transmission efficiency and shows superior resilience to optical pointing jitter.
format Preprint
id arxiv_https___arxiv_org_abs_2507_08490
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neuromorphic Split Computing via Optical Inter-Satellite Links
Song, Zihang
Popovski, Petar
Image and Video Processing
We present a neuromorphic split-computing framework for energy-efficient low-latency inference over optical inter-satellite links. The system partitions a spiking neural network (SNN) between edge and core nodes. To transmit sparse spiking features efficiently, we introduce a lossless channel-block-sparse event representation that exploits inter- and intra-channel sparsity. We employ hierarchical error protection using multi-level forward error correction and cyclic redundancy checks to ensure reliable communication without retransmission. The framework uses end-to-end training with sparsity and clustering regularizers, combined with channel-aware stochastic masking to optimize feature compression and channel robustness jointly. In a proof-of-concept implementation on remote sensing imagery, the framework achieves over $10 \times$ reduction in both computational energy and transmission load compared to conventional dense split systems, with less than 1% accuracy loss. The proposed approach also outperforms address-event-based split SNNs by $3.7 \times$ in transmission efficiency and shows superior resilience to optical pointing jitter.
title Neuromorphic Split Computing via Optical Inter-Satellite Links
topic Image and Video Processing
url https://arxiv.org/abs/2507.08490