用脉冲神经网络实现低功耗实时脑活动解码，助力无线神经假体发展
Realtime-Capable Hybrid Spiking Neural Networks for Neural Decoding of Cortical Activity
- 设计轻量级脉冲神经网络，结合压缩技术提升解码效率
- 在灵长类抓取数据集上超越现有最优性能，功耗与体积相近
- 实现真正实时解码，适合植入式神经接口场景
皮层内脑机接口（iBMIs）为恢复因损伤丧失的脑活动提供了有前景的解决方案。然而，使用此类神经假体的患者因设备布线庞大而需永久性颅骨开孔。这推动了无线iBMIs的发展，其要求低功耗和小体积。近期，脉冲神经网络（SNNs）被研究作为低功耗神经解码的潜在候选方案。本文基于2024年非人灵长类运动控制神经解码挑战赛的最新成果，优化模型架构，在保持类似资源消耗的前提下，超越了现有最先进方法在Primate Reaching数据集上的表现。我们进一步实现可实时运行的模型版本，并讨论该架构的深远影响。本工作朝着使用类脑硬件实现无延迟皮层尖峰信号解码迈出关键一步，有望显著改善数百万瘫痪患者的生活质量。
原文摘要 · Abstract (English)
Intra-cortical brain-machine interfaces (iBMIs) present a promising solution to restoring and decoding brain activity lost due to injury. However, patients with such neuroprosthetics suffer from permanent skull openings resulting from the devices' bulky wiring. This drives the development of wireless iBMIs, which demand low power consumption and small device footprint. Most recently, spiking neural networks (SNNs) have been researched as potential candidates for low-power neural decoding. In this work, we present the next step of utilizing SNNs for such tasks, building on the recently published results of the 2024 Grand Challenge on Neural Decoding Challenge for Motor Control of non-Human Primates. We optimize our model architecture to exceed the existing state of the art on the Primate Reaching dataset while maintaining similar resource demand through various compression techniques. We further focus on implementing a realtime-capable version of the model and discuss the implications of this architecture. With this, we advance one step towards latency-free decoding of cortical spike trains using neuromorphic technology, ultimately improving the lives of millions of paralyzed patients.
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。