通过光链路实现神经形态分层计算，大幅降低星上推理能耗与传输负载。
Neuromorphic Split Computing via Optical Inter-Satellite Links
- 将脉冲神经网络分拆至边缘与核心节点，利用稀疏事件编码高效传输。
- 相比传统系统，计算能耗和传输量均降低10倍以上，精度损失小于1%。
- 适合低功耗、高可靠性的星载实时智能处理场景，如遥感图像分析。
我们提出一种基于光学星间链路的神经形态分层计算框架，实现能量高效、低延迟的推理。该系统将脉冲神经网络（SNN）在边缘与核心节点间进行分割。为高效传输稀疏的脉冲特征，引入无损的通道块稀疏事件表示，利用通道间与通道内稀疏性。采用多级前向纠错与循环冗余校验实现分层错误保护，确保可靠通信且无需重传。框架采用端到端训练，结合稀疏性与聚类正则化，并通过通道感知的随机掩码优化特征压缩与信道鲁棒性。在遥感图像的原型实现中，相比传统密集型分层系统，计算能耗和传输负载均降低超过10倍，精度损失低于1%。该方法在传输效率上比基于地址-事件的分层SNN提升3.7倍，且对光学指向抖动具有更强鲁棒性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。