PulseAugur
中
实时 18:42:43
English(EN) End-to-End Radar and Communication Modulation Recognition with Neuromorphic Computing

神经形态EMRFormer在调制识别方面实现90%的能耗降低

研究人员开发了EMRFormer,这是一种新颖的脉冲神经网络(SNN)架构,专为资源受限的神经形态硬件上的端到端自动调制识别(AMR)而设计。该架构集成了脉冲驱动的Transformer与自适应脉冲编码和整数泄漏积分-发放(Leaky Integrate-and-Fire)神经元,以提高信息保持能力和表征能力。EMRFormer还集成了脉冲可分离卷积神经网络(CNN),用于从原始IQ波形中提取多尺度时间特征,在实现最先进的准确率的同时,与传统的深度学习方法相比,理论能耗降低了90%以上。在KA200神经形态芯片上的评估显示,与在3090 GPU或Orin NX上运行相比,功耗降低了五倍,展示了其在边缘设备上进行AMR的潜力。 AI

影响 赋能资源受限的边缘设备上更节能的AI应用。

排序理由 该集群包含一篇arXiv预印本,详细介绍了一种新的神经网络架构及其性能评估。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

神经形态EMRFormer在调制识别方面实现90%的能耗降低

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群包含一篇arXiv预印本,详细介绍了一种新的神经网络架构及其性能评估。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
106 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Xiaohu Li, Chongxiao Qu, Caiyong Lin, Chenxiao Dou, Wei Hua ·

    基于神经形态计算的端到端雷达与通信调制识别

    arXiv:2606.24075v1 Announce Type: cross Abstract: Although deep learning-based methods can achieve high accuracy in automatic modulation recognition (AMR) tasks, their high computational cost makes it difficult to strike a balance between accuracy and power consumption, thereby l…